Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2762 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3472. Min Range: -10.3472
Max Act: 10.3472. Min Act: -0.1700
Data Index: 5891116 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3472. Min Range: -10.3472
Max Act: 10.2222. Min Act: -0.1700
Data Index: 4628779 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3472. Min Range: -10.3472
Max Act: 10.1597. Min Act: -0.1700
Data Index: 769910 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3472. Min Range: -10.3472
Max Act: 10.1597. Min Act: -0.1700
Data Index: 6346777 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3472. Min Range: -10.3472
Max Act: 10.0972. Min Act: -0.1700
Data Index: 2090229 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3472. Min Range: -10.3472
Max Act: 10.0347. Min Act: -0.1700
Data Index: 8367629 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.9097. Min Act: -0.1700
Data Index: 8367635 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.8472. Min Act: -0.1700
Data Index: 6801858 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.8472. Min Act: -0.1700
Data Index: 8416592 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.8472. Min Act: -0.1700
Data Index: 1706489 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.7847. Min Act: -0.1700
Data Index: 794659 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.7847. Min Act: -0.1700
Data Index: 5606332 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.5972. Min Act: -0.1697
Data Index: 8447728 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.5972. Min Act: -0.1700
Data Index: 7058847 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.5347. Min Act: -0.1700
Data Index: 2583872 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.4722. Min Act: -0.1700
Data Index: 1952770 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.4722. Min Act: -0.1700
Data Index: 8548611 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.4722. Min Act: -0.1700
Data Index: 5282472 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.4097. Min Act: -0.1700
Data Index: 3562536 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3472. Min Range: -10.3472
Max Act: 9.4097. Min Act: -0.1700
Data Index: 6230773 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19