Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.9802. Min Act: -0.1700
Data Index: 2652032 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.9169. Min Act: -0.1700
Data Index: 3380641 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.9169. Min Act: -0.1700
Data Index: 7945839 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8852. Min Act: -0.1700
Data Index: 5391651 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8852. Min Act: -0.1700
Data Index: 835953 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8852. Min Act: -0.1700
Data Index: 296004 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8852. Min Act: -0.1700
Data Index: 8539292 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8693. Min Act: -0.1700
Data Index: 4645834 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8693. Min Act: -0.1700
Data Index: 7656811 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8376. Min Act: -0.1700
Data Index: 5284815 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8534. Min Act: -0.1700
Data Index: 1304419 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8534. Min Act: -0.1700
Data Index: 8754713 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8534. Min Act: -0.1700
Data Index: 8822895 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8217. Min Act: -0.1700
Data Index: 7441956 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8534. Min Act: -0.1700
Data Index: 6803687 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.7898. Min Act: -0.1700
Data Index: 6869149 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.7898. Min Act: -0.1700
Data Index: 1794544 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.8057. Min Act: -0.1700
Data Index: 2762572 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.7739. Min Act: -0.1700
Data Index: 683137 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9802. Min Range: -2.9802
Max Act: 2.7898. Min Act: -0.1700
Data Index: 4533197 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19