Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.5404. Min Act: -0.1700
Data Index: 2067423 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.1029. Min Act: -0.1700
Data Index: 6557743 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0717. Min Act: -0.1700
Data Index: 7563907 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0717. Min Act: -0.1700
Data Index: 995658 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0404. Min Act: -0.1700
Data Index: 6965730 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0092. Min Act: -0.1700
Data Index: 6698007 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0092. Min Act: -0.1700
Data Index: 3553232 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5404. Min Range: -7.5404
Max Act: 7.0092. Min Act: -0.1700
Data Index: 28701 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9779. Min Act: -0.1700
Data Index: 5711737 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9779. Min Act: -0.1700
Data Index: 1251109 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9467. Min Act: -0.1700
Data Index: 6522656 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9467. Min Act: -0.1700
Data Index: 1995425 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.9154. Min Act: -0.1700
Data Index: 5092378 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8842. Min Act: -0.1700
Data Index: 8407902 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8529. Min Act: -0.1700
Data Index: 5612349 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8529. Min Act: -0.1700
Data Index: 3982720 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 3427915 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 3183092 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8217. Min Act: -0.1700
Data Index: 235752 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5404. Min Range: -7.5404
Max Act: 6.8529. Min Act: -0.1700
Data Index: 4967585 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19