Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3653. Min Range: -12.3653
Max Act: 12.3653. Min Act: -0.1700
Data Index: 8577420 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3653. Min Range: -12.3653
Max Act: 12.3028. Min Act: -0.1700
Data Index: 1041528 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.8653. Min Act: -0.1700
Data Index: 3393653 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.8653. Min Act: -0.1700
Data Index: 4311658 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.8653. Min Act: -0.1700
Data Index: 1045876 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.8028. Min Act: -0.1700
Data Index: 2352701 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.6778. Min Act: -0.1700
Data Index: 3212345 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.6153. Min Act: -0.1700
Data Index: 1244212 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.6153. Min Act: -0.1700
Data Index: 1144138 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.5528. Min Act: -0.1700
Data Index: 1780067 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.5528. Min Act: -0.1700
Data Index: 6724626 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4903. Min Act: -0.1700
Data Index: 2887801 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4903. Min Act: -0.1700
Data Index: 3271758 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4278. Min Act: -0.1700
Data Index: 1311492 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4278. Min Act: -0.1700
Data Index: 339691 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4278. Min Act: -0.1700
Data Index: 5580501 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4278. Min Act: -0.1700
Data Index: 4667200 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.4278. Min Act: -0.1700
Data Index: 2133436 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.3653. Min Act: -0.1700
Data Index: 4456395 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3653. Min Range: -12.3653
Max Act: 11.3653. Min Act: -0.1700
Data Index: 646844 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19