Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 387 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.6841. Min Act: -0.1700
Data Index: 4847862 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5589. Min Act: -0.1700
Data Index: 286868 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5902. Min Act: -0.1700
Data Index: 780894 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5745. Min Act: -0.1700
Data Index: 6119845 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5589. Min Act: -0.1700
Data Index: 3893277 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5432. Min Act: -0.1700
Data Index: 2024578 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5275. Min Act: -0.1700
Data Index: 187161 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5432. Min Act: -0.1700
Data Index: 4302180 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5432. Min Act: -0.1700
Data Index: 2183527 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5119. Min Act: -0.1700
Data Index: 6119846 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4962. Min Act: -0.1700
Data Index: 6128540 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5275. Min Act: -0.1700
Data Index: 488813 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.5119. Min Act: -0.1700
Data Index: 6210727 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4962. Min Act: -0.1700
Data Index: 5926045 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4649. Min Act: -0.1700
Data Index: 4126054 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4649. Min Act: -0.1700
Data Index: 527936 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4492. Min Act: -0.1700
Data Index: 7641483 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4649. Min Act: -0.1700
Data Index: 2903145 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4492. Min Act: -0.1700
Data Index: 5284672 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6841. Min Range: -3.6841
Max Act: 3.4336. Min Act: -0.1700
Data Index: 4823391 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19