Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.7715. Min Act: -0.1700
Data Index: 952576 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.6152. Min Act: -0.1700
Data Index: 4840927 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.5215. Min Act: -0.1700
Data Index: 3475049 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.5215. Min Act: -0.1700
Data Index: 6894368 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.4590. Min Act: -0.1700
Data Index: 4245047 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.4277. Min Act: -0.1700
Data Index: 6986953 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.4277. Min Act: -0.1700
Data Index: 850294 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.3340. Min Act: -0.1700
Data Index: 3962869 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.3340. Min Act: -0.1700
Data Index: 7050558 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.3652. Min Act: -0.1700
Data Index: 341583 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.3027. Min Act: -0.1700
Data Index: 590529 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.3027. Min Act: -0.1700
Data Index: 7490771 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.3027. Min Act: -0.1700
Data Index: 3093567 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2715. Min Act: -0.1700
Data Index: 8767151 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2715. Min Act: -0.1700
Data Index: 490362 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2715. Min Act: -0.1700
Data Index: 3073523 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2402. Min Act: -0.1700
Data Index: 600080 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2090. Min Act: -0.1700
Data Index: 3835550 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2090. Min Act: -0.1700
Data Index: 6264335 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7715. Min Range: -6.7715
Max Act: 6.2090. Min Act: -0.1700
Data Index: 1315873 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19