Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0216. Min Range: -6.0216
Max Act: 6.0216. Min Act: -0.1700
Data Index: 3371191 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.9278. Min Act: -0.1700
Data Index: 676514 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.8341. Min Act: -0.1700
Data Index: 7021213 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.7403. Min Act: -0.1700
Data Index: 762834 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.7091. Min Act: -0.1700
Data Index: 8758145 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6778. Min Act: -0.1700
Data Index: 7975111 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6778. Min Act: -0.1700
Data Index: 3567347 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6778. Min Act: -0.1700
Data Index: 1056350 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6466. Min Act: -0.1700
Data Index: 6527417 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6466. Min Act: -0.1700
Data Index: 5759899 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6153. Min Act: -0.1700
Data Index: 5929433 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6153. Min Act: -0.1700
Data Index: 3768571 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6153. Min Act: -0.1700
Data Index: 6019766 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.6153. Min Act: -0.1700
Data Index: 3356562 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.5528. Min Act: -0.1700
Data Index: 4855963 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.5528. Min Act: -0.1700
Data Index: 887490 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.5528. Min Act: -0.1700
Data Index: 3772308 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.5216. Min Act: -0.1700
Data Index: 5319247 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.5216. Min Act: -0.1700
Data Index: 4152318 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0216. Min Range: -6.0216
Max Act: 5.5528. Min Act: -0.1700
Data Index: 8199084 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19