Home › Census › gelu

gelu

Syntologyfunction-name censuscensus 2026-09-22battery b986f7e04d79all samples with this name

gelu: 43 implementations from 74 papers ran on one shared input (census 2026-09-22, battery b986f7e04d79); they produced 6 distinct outputs.

Identical values to six decimals (the recorded digest) on the shared input are agreement on those inputs, not equivalence. Implementations are compared only within one bucket, the positional (rank, kind, dtype) of each array argument; the argument name is not part of the key because the harness draws the shared array from (rank, kind) and casts it to the dtype, whatever the name; each bucket's shared input is fixed by that key, so members of one bucket saw bitwise-identical inputs under their own scalar arguments. A cluster is the set of members whose recorded output digest is identical. Nothing here says which computation a paper's method intended, and nothing reproduces a paper's results. Each member's behaviour fingerprint (its outputs on the shared battery) is not in this export and is not shown here; get_code(code_sha256="…") returns this sample's fingerprint on the shared battery, with the battery's shuffled null and lift; not shown on this site (how to connect); click a member's code_sha256 to copy that call.

Not compared, and not in the tables or the counts above:

Bucket 1 of 1: arg 1: rank 2, kind float, dtype float32

43 implementations from 74 papers share this bucket (rank, kind, dtype of each array argument, positional; each member's recorded signature, argument name included, is shown under it); 6 distinct outputs, largest cluster first. Values are the first 8 of the recorded output, flattened.

Cluster (same digest to six decimals)MembersShared output on this bucket's input
31 implementations
54 papers
ae7f1a8a01e3
recorded values differ by up to 5.96e-08
one code sha held from 12 papers' repositories
modeling_bert.py fdc64f4c72036ae4
recorded x:2/float/float32
one code sha held from 4 papers' repositories
modeling.py 40e9fee2e0b7e278
recorded x:2/float/float32
one code sha held from 3 papers' repositories
models/MELT_FMLP.py 56a9ab06b860b180
recorded x:2/float/float32
one code sha held from 3 papers' repositories
continuous_transformer/ContSpaceTime.py 62e7409a816626ac
recorded x:2/float/float32
one code sha held from 2 papers' repositories
models/transformers/modeling_bert.py 211753ba29188d4e
recorded x:2/float/float32
one code sha held from 2 papers' repositories
src/models/TSR_model.py 50e1ffed03f484ec
recorded x:2/float/float32
one code sha held from 2 papers' repositories
src/model/transformer.py 66c21a3911091d29
recorded x:2/float/float32
one code sha held from 2 papers' repositories
models/model.py 9d64df741b029314
recorded x:2/float/float32
one code sha held from 2 papers' repositories
vlcgan/model.py a3abf3fe697fabd0
recorded x:2/float/float32
one code sha held from 2 papers' repositories
src/model.py a43d18e9c8836542
recorded x:2/float/float32
one code sha held from 2 papers' repositories
model.py be4a5b4fd2623b72
recorded x:2/float/float32
one code sha held from 2 papers' repositories
model/ce.py c2f0705ed8e6f7e6
recorded x:2/float/float32
one code sha held from 2 papers' repositories
src/model/sequential/fmlprec.py eb13ab048d49bf28
recorded x:2/float/float32

spikeLM-BERT/spike_bert.py 067fa79dc5c16d05
recorded x:2/float/float32

textgen/language_modeling/songnet_model.py 2214122297c45b69
recorded x:2/float/float32

model/squidnet.py 29af270e862dd867
recorded x:2/float/float32

transformer/modeling_bert_quant.py 2d588601e8e99f5d
recorded x:2/float/float32

model.py 344a09e8f735a6b3
recorded x:2/float/float32

src/modeling.py 3c06d11eadebd504
recorded x:2/float/float32

chinese_gpt/gpt_modeling.py 409ea40d28f93c7e
recorded x:2/float/float32

DynaBERT/transformers/modeling_bert.py 4ac7efa4e6383d65
recorded x:2/float/float32

src/rtransformer/model.py 69e3a274f98c15af
recorded x:2/float/float32

models/TransGAN_8_8_1.py 6a9faa89f4d1a831
recorded x:2/float/float32

moco/GCN_Transformer_mask.py 6f324d970195cc1d
recorded x:2/float/float32

model/rnalm/modeling_rnalm.py 82a647d4d28fc62b
recorded x:2/float/float32

run_hbm.py 835ff702d75feb5b
recorded x:2/float/float32

rosita/modeling/pretrain_tasks/rosita.py 8d619e54294fb0b7
recorded x:2/float/float32

relogic/logickit/inference/modeling.py 90e5e96897d48ebb
recorded x:2/float/float32

model/modeling_genmc.py a8eafe3c0d1e9892
recorded x:2/float/float32

modeling.py e650dcdf9e8a559f
recorded x:2/float/float32

src/train/model/transformer.py f6ed858344bb92c7
recorded x:2/float/float32
[1.73823, -0.095926, 0.325136, -0.169142, -0.165495, -0.156008, -0.16817, 0.410555, …]
shape [4, 8] · float32 · Tensor
7 implementations
13 papers
fbdb323a3bf0
recorded values differ by up to 1.19e-07
same digest as torch: tanh
one code sha held from 4 papers' repositories
gpt/examples/NLG/src/model_nola.py 8d23fbe2b99b840b
recorded x:2/float/float32
one code sha held from 3 papers' repositories
recbole/model/sequential_recommender/sasrec.py d9dcfb510a5e2690
recorded x:2/float/float32
one code sha held from 2 papers' repositories
JGA-LBD/DDBM/ddbm/unet3d.py f51cf2cbd3e598d8
recorded x:2/float/float32

lopuhin_transformer_lm/lm/model.py 0e399e430fc4851d
recorded x:2/float/float32; c=0.7978845608028654

model.py 52548f442af51038
recorded x:2/float/float32; dataset='IEMOCAP'

modeling_gnn.py b75e9c793d2a286a
recorded x:2/float/float32

models/transformer.py d60ff4b7f07480e1
recorded x:2/float/float32
[1.73817, -0.0961344, 0.325121, -0.169195, -0.165613, -0.156171, -0.168216, 0.410527, …]
shape [4, 8] · float32 · Tensor
2 implementations
5 papers
1348f288d0c7
recorded values identical
same digest as torch: exact
one code sha held from 3 papers' repositories
zerosyl/zerosyl.py f30ebf4e48b7e2d7
recorded x:2/float/float32
one code sha held from 2 papers' repositories
model/supernet_transformer.py 08a5be1ffa0676e3
recorded x:2/float/float32
[1.73823, -0.095926, 0.325136, -0.169142, -0.165495, -0.156008, -0.16817, 0.410555, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
15d2e6cc373b

hetseq/bert_modeling.py 1ada98e81f3ec64a
recorded x:2/float/float32
[1.73823, -0.0959253, 0.325136, -0.169141, -0.165494, -0.156007, -0.16817, 0.410556, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
7a843be0cfb0

maskclip/modeling/maskclip.py 08eccabe0923b8c0
recorded x:2/float/float32
[1.72251, -0.105012, 0.329506, -0.162906, -0.159825, -0.152057, -0.162063, 0.41599, …]
shape [4, 8] · float32 · Tensor
1 implementation
1 paper
d37efaa41103

modules/transformer.py 8c106eab341fc5d3
recorded x:2/float/float32
[1.79249, -0.0215912, 0.366314, -0.10066, -0.0789239, -0.0645493, -0.1029, 0.464664, …]
shape [4, 8] · float32 · Tensor

Identical values to six decimals (the recorded digest) on the shared input are agreement on those inputs, not equivalence; where a cluster's members carry recorded values, the largest difference among them is shown under the cluster. Paper titles are the archive's archive 2025-07-28 where the paper is in the archive and the graph's where it was added by Syntology; papers with no page here are shown by their recorded paper id only. A paper count above the implementation count means one implementation (one code sha) is held from several papers' repositories and counts once. Per-sample status, licence and fingerprint records for each paper are on its paper page. JSON twin: /census/gelu.json.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections