Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4112 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3689. Min Range: -6.3689
Max Act: 6.3689. Min Act: -0.1700
Data Index: 6299174 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3689. Min Range: -6.3689
Max Act: 6.2439. Min Act: -0.1700
Data Index: 4722150 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.7439. Min Act: -0.1700
Data Index: 2307755 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.7439. Min Act: -0.1700
Data Index: 184270 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.6814. Min Act: -0.1700
Data Index: 759709 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.6502. Min Act: -0.1700
Data Index: 4865650 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.6502. Min Act: -0.1700
Data Index: 7608390 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.6502. Min Act: -0.1700
Data Index: 4348759 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5877. Min Act: -0.1700
Data Index: 995333 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5877. Min Act: -0.1700
Data Index: 146826 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 474037 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 7316684 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 1992413 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 3498175 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5564. Min Act: -0.1700
Data Index: 7178586 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 7885010 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4770977 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 8328438 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 1457121 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3689. Min Range: -6.3689
Max Act: 5.5252. Min Act: -0.1700
Data Index: 4658255 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19