Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.8649. Min Act: -0.1700
Data Index: 1256308 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.7242. Min Act: -0.1700
Data Index: 6282766 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.7085. Min Act: -0.1700
Data Index: 2258019 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6929. Min Act: -0.1700
Data Index: 517338 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6929. Min Act: -0.1700
Data Index: 1881350 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6772. Min Act: -0.1700
Data Index: 5307818 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6616. Min Act: -0.1700
Data Index: 2619945 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6616. Min Act: -0.1700
Data Index: 4264285 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6459. Min Act: -0.1700
Data Index: 4407797 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6303. Min Act: -0.1700
Data Index: 8448323 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6303. Min Act: -0.1700
Data Index: 8582267 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.6146. Min Act: -0.1700
Data Index: 351352 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5833. Min Act: -0.1700
Data Index: 2341584 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5677. Min Act: -0.1700
Data Index: 3439559 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5833. Min Act: -0.1700
Data Index: 456019 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5833. Min Act: -0.1700
Data Index: 2436102 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5990. Min Act: -0.1700
Data Index: 6425763 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5677. Min Act: -0.1700
Data Index: 5275127 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5520. Min Act: -0.1700
Data Index: 5787675 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8649. Min Range: -3.8649
Max Act: 3.5207. Min Act: -0.1700
Data Index: 2379450 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19