{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/knowledge-neurons-in-pretrained-transformers","title":"Knowledge Neurons in Pretrained Transformers","arxiv_id":"2104.08696","date":"2021-04-18","proceeding":"ACL 2022 5","authors":["Damai Dai","Li Dong","Yaru Hao","Zhifang Sui","Baobao Chang","Furu Wei"],"abstract":"Large-scale pretrained language models are surprisingly good at recalling factual knowledge presented in the training corpus. In this paper, we present preliminary studies on how factual knowledge is stored in pretrained Transformers by introducing the concept of knowledge neurons. Specifically, we examine the fill-in-the-blank cloze task for BERT. Given a relational fact, we propose a knowledge attribution method to identify the neurons that express the fact. We find that the activation of such knowledge neurons is positively correlated to the expression of their corresponding facts. In our case studies, we attempt to leverage knowledge neurons to edit (such as update, and erase) specific factual knowledge without fine-tuning. Our results shed light on understanding the storage of knowledge within pretrained Transformers. The code is available at https://github.com/Hunter-DDM/knowledge-neurons.","url_abs":"https://arxiv.org/abs/2104.08696v2","url_pdf":"https://arxiv.org/pdf/2104.08696v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"knowledge-neurons-in-pretrained-transformers","repo_url":"https://github.com/hunter-ddm/knowledge-neurons","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-neurons-in-pretrained-transformers","repo_url":"https://github.com/EleutherAI/knowledge-neurons","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"knowledge-neurons-in-pretrained-transformers","repo_url":"https://github.com/kmeng01/rome","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2104.08696","atlas_url":"https://app.syntology.ai/?focus=2104.08696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08696"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EleutherAI/knowledge-neurons","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kmeng01/rome","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hunter-ddm/knowledge-neurons","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":2,"ran":1,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e01867c63efbe404","entry":"KnowledgeNeurons","repo":"EleutherAI/knowledge-neurons","repo_kind":"listed","path":"knowledge_neurons/knowledge_neurons.py","file_url":"https://github.com/EleutherAI/knowledge-neurons/blob/HEAD/knowledge_neurons/knowledge_neurons.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e01867c63efbe404"}},{"code_sha256_prefix":"2fa69435832209b8","entry":"parse_kn","repo":"hunter-ddm/knowledge-neurons","repo_kind":"official","path":"src/2_get_kn.py","file_url":"https://github.com/hunter-ddm/knowledge-neurons/blob/HEAD/src/2_get_kn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2fa69435832209b8"}},{"code_sha256_prefix":"76d0168ed08b2e79","entry":"KnowledgeNeurons","repo":"kmeng01/rome","repo_kind":"listed","path":"baselines/kn/knowledge_neurons/knowledge_neurons/knowledge_neurons.py","file_url":"https://github.com/kmeng01/rome/blob/HEAD/baselines/kn/knowledge_neurons/knowledge_neurons/knowledge_neurons.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76d0168ed08b2e79"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}