Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.5005. Min Act: -0.1700
Data Index: 866813 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.3755. Min Act: -0.1700
Data Index: 312082 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.2817. Min Act: -0.1700
Data Index: 1734683 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.2505. Min Act: -0.1700
Data Index: 4566826 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.1567. Min Act: -0.1700
Data Index: 8211141 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.1567. Min Act: -0.1700
Data Index: 4085311 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.1255. Min Act: -0.1700
Data Index: 8571562 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0630. Min Act: -0.1700
Data Index: 7880451 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0317. Min Act: -0.1700
Data Index: 3858781 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0005. Min Act: -0.1700
Data Index: 654702 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0317. Min Act: -0.1700
Data Index: 4048463 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0005. Min Act: -0.1700
Data Index: 513950 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0005. Min Act: -0.1700
Data Index: 7797721 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5005. Min Range: -6.5005
Max Act: 6.0005. Min Act: -0.1700
Data Index: 4908850 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5005. Min Range: -6.5005
Max Act: 5.9692. Min Act: -0.1700
Data Index: 5675009 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5005. Min Range: -6.5005
Max Act: 5.9692. Min Act: -0.1700
Data Index: 1787609 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5005. Min Range: -6.5005
Max Act: 5.9380. Min Act: -0.1700
Data Index: 7510087 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5005. Min Range: -6.5005
Max Act: 5.9380. Min Act: -0.1700
Data Index: 1418249 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5005. Min Range: -6.5005
Max Act: 5.9380. Min Act: -0.1700
Data Index: 1989429 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5005. Min Range: -6.5005
Max Act: 5.9380. Min Act: -0.1700
Data Index: 2793200 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19