Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5785 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4808. Min Range: -9.4808
Max Act: 9.4808. Min Act: -0.1700
Data Index: 5544669 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4808. Min Range: -9.4808
Max Act: 9.1058. Min Act: -0.1700
Data Index: 4776632 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.9808. Min Act: -0.1700
Data Index: 1974169 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.9183. Min Act: -0.1700
Data Index: 2712174 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.8558. Min Act: -0.1700
Data Index: 4636848 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.8558. Min Act: -0.1700
Data Index: 3242930 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.7933. Min Act: -0.1700
Data Index: 4648661 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.7308. Min Act: -0.1700
Data Index: 6700192 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.7933. Min Act: -0.1700
Data Index: 2852034 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.7308. Min Act: -0.1700
Data Index: 8068370 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.7308. Min Act: -0.1700
Data Index: 2712170 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.7308. Min Act: -0.1700
Data Index: 4279537 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.6683. Min Act: -0.1700
Data Index: 3688454 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.6058. Min Act: -0.1700
Data Index: 3559408 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.6058. Min Act: -0.1700
Data Index: 2712164 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.5433. Min Act: -0.1700
Data Index: 2712171 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.4808. Min Act: -0.1700
Data Index: 7333464 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.5433. Min Act: -0.1700
Data Index: 2700059 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.5433. Min Act: -0.1700
Data Index: 5815223 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4808. Min Range: -9.4808
Max Act: 8.4808. Min Act: -0.1700
Data Index: 143806 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19