Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3451 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3368. Min Range: -8.3368
Max Act: 8.3368. Min Act: -0.1700
Data Index: 160759 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3368. Min Range: -8.3368
Max Act: 8.0868. Min Act: -0.1700
Data Index: 8046872 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3368. Min Range: -8.3368
Max Act: 8.0243. Min Act: -0.1700
Data Index: 4242670 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.8993. Min Act: -0.1700
Data Index: 4875101 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.7431. Min Act: -0.1700
Data Index: 5863963 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.7743. Min Act: -0.1700
Data Index: 3547073 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.7743. Min Act: -0.1700
Data Index: 143209 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.7431. Min Act: -0.1700
Data Index: 7580963 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.6493. Min Act: -0.1700
Data Index: 3302334 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.6806. Min Act: -0.1700
Data Index: 5610241 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.6181. Min Act: -0.1700
Data Index: 862330 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.5868. Min Act: -0.1700
Data Index: 3062522 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.5868. Min Act: -0.1700
Data Index: 8269847 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.5868. Min Act: -0.1700
Data Index: 4423763 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.5243. Min Act: -0.1700
Data Index: 1055443 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.5243. Min Act: -0.1700
Data Index: 8097408 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.4931. Min Act: -0.1700
Data Index: 2604063 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.4618. Min Act: -0.1700
Data Index: 1777659 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.4618. Min Act: -0.1700
Data Index: 1770167 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3368. Min Range: -8.3368
Max Act: 7.4618. Min Act: -0.1700
Data Index: 1424707 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19