Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.9164. Min Act: -0.1700
Data Index: 2139569 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.8226. Min Act: -0.1700
Data Index: 3917541 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.8539. Min Act: -0.1700
Data Index: 2139568 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.7601. Min Act: -0.1700
Data Index: 3917539 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.7601. Min Act: -0.1700
Data Index: 2139566 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.6349. Min Act: -0.1700
Data Index: 3917540 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.5880. Min Act: -0.1700
Data Index: 8716248 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.5567. Min Act: -0.1700
Data Index: 1977610 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.6036. Min Act: -0.1700
Data Index: 758894 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.5097. Min Act: -0.1700
Data Index: 1977611 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.4940. Min Act: -0.1700
Data Index: 3917543 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.4784. Min Act: -0.1700
Data Index: 2978706 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.4000. Min Act: -0.1700
Data Index: 758896 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.4157. Min Act: -0.1700
Data Index: 3917538 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.3530. Min Act: -0.1700
Data Index: 3917542 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.3373. Min Act: -0.1700
Data Index: 1026445 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.3216. Min Act: -0.1700
Data Index: 1079182 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.3059. Min Act: -0.1700
Data Index: 2139567 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.2273. Min Act: -0.1700
Data Index: 758898 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9164. Min Range: -3.9164
Max Act: 3.2431. Min Act: -0.1700
Data Index: 6683866 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19