Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.7473. Min Act: -0.1700
Data Index: 679090 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.7473. Min Act: -0.1700
Data Index: 679091 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.6848. Min Act: -0.1700
Data Index: 7660947 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.6848. Min Act: -0.1700
Data Index: 5510825 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.6848. Min Act: -0.1700
Data Index: 4339385 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.6223. Min Act: -0.1700
Data Index: 1735891 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.6223. Min Act: -0.1700
Data Index: 6929447 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.6223. Min Act: -0.1700
Data Index: 8296347 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.5598. Min Act: -0.1700
Data Index: 7322570 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.5598. Min Act: -0.1700
Data Index: 7163499 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.5598. Min Act: -0.1700
Data Index: 5558446 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.4973. Min Act: -0.1700
Data Index: 5087136 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.4348. Min Act: -0.1700
Data Index: 8280464 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.4348. Min Act: -0.1700
Data Index: 857359 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.4348. Min Act: -0.1700
Data Index: 7650168 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.3723. Min Act: -0.1700
Data Index: 6202644 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.3723. Min Act: -0.1700
Data Index: 2369334 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.3723. Min Act: -0.1700
Data Index: 7121422 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.3098. Min Act: -0.1700
Data Index: 560122 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7473. Min Range: -12.7473
Max Act: 12.3098. Min Act: -0.1700
Data Index: 1860342 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19