Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 287 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.7409. Min Act: -0.1700
Data Index: 3571406 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.7409. Min Act: -0.1700
Data Index: 2932923 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.6784. Min Act: -0.1700
Data Index: 278153 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.5534. Min Act: -0.1700
Data Index: 8383886 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.6159. Min Act: -0.1700
Data Index: 2591519 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.4909. Min Act: -0.1700
Data Index: 4658879 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.4909. Min Act: -0.1700
Data Index: 3652683 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.4284. Min Act: -0.1700
Data Index: 1162849 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.4909. Min Act: -0.1700
Data Index: 1344865 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 7908806 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3659. Min Act: -0.1700
Data Index: 1458154 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3659. Min Act: -0.1700
Data Index: 7625740 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3659. Min Act: -0.1700
Data Index: 4934418 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.4284. Min Act: -0.1700
Data Index: 2044523 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 32 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 2695527 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 7042416 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 3072507 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 8273892 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7409. Min Range: -10.7409
Max Act: 10.3034. Min Act: -0.1700
Data Index: 3135817 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19