Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3937 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.6007. Min Act: -0.1700
Data Index: 2362904 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.5695. Min Act: -0.1700
Data Index: 6916027 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.5070. Min Act: -0.1700
Data Index: 7488815 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3820. Min Act: -0.1700
Data Index: 841278 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3820. Min Act: -0.1700
Data Index: 2492054 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3820. Min Act: -0.1700
Data Index: 71331 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3195. Min Act: -0.1700
Data Index: 1206967 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3507. Min Act: -0.1700
Data Index: 6696199 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2882. Min Act: -0.1700
Data Index: 1393826 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3195. Min Act: -0.1700
Data Index: 1350918 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3195. Min Act: -0.1700
Data Index: 4929525 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3195. Min Act: -0.1700
Data Index: 8306147 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3195. Min Act: -0.1700
Data Index: 2301414 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.3195. Min Act: -0.1700
Data Index: 4738033 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2882. Min Act: -0.1700
Data Index: 6053498 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2882. Min Act: -0.1700
Data Index: 3451172 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2882. Min Act: -0.1700
Data Index: 2584537 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2882. Min Act: -0.1700
Data Index: 7445338 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2257. Min Act: -0.1700
Data Index: 5941168 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6007. Min Range: -5.6007
Max Act: 5.2570. Min Act: -0.1700
Data Index: 1912019 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19