Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.7986. Min Act: -0.1700
Data Index: 6573142 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.7361. Min Act: -0.1700
Data Index: 8782888 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.6736. Min Act: -0.1700
Data Index: 7487727 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.6111. Min Act: -0.1700
Data Index: 5625364 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.4861. Min Act: -0.1700
Data Index: 6604373 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 4399936 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 3366017 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 5468188 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 7487726 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.6111. Min Act: -0.1700
Data Index: 7863096 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 8580330 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.6111. Min Act: -0.1700
Data Index: 3458345 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.4861. Min Act: -0.1700
Data Index: 7977794 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.4861. Min Act: -0.1700
Data Index: 3785172 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.4861. Min Act: -0.1700
Data Index: 6573141 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 5603723 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.5486. Min Act: -0.1700
Data Index: 5013589 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.4236. Min Act: -0.1700
Data Index: 7844027 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.4236. Min Act: -0.1700
Data Index: 2085109 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7986. Min Range: -7.7986
Max Act: 7.3924. Min Act: -0.1700
Data Index: 2974907 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19