Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.7984. Min Act: -0.1700
Data Index: 63643 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.7046. Min Act: -0.1700
Data Index: 8354969 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.6109. Min Act: -0.1700
Data Index: 5717533 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.5171. Min Act: -0.1700
Data Index: 2215112 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.5171. Min Act: -0.1700
Data Index: 7809663 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.4546. Min Act: -0.1700
Data Index: 8644356 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.4546. Min Act: -0.1700
Data Index: 2977672 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 5760161 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3921. Min Act: -0.1700
Data Index: 7049144 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3921. Min Act: -0.1700
Data Index: 7528093 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 3524776 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 198866 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 180671 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 2996805 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 340879 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1125619 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 7720926 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 1867101 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 5913392 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7984. Min Range: -4.7984
Max Act: 4.3609. Min Act: -0.1700
Data Index: 2313111 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19