Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4835 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.7156. Min Act: -0.1700
Data Index: 5464028 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.6844. Min Act: -0.1700
Data Index: 32294 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.6219. Min Act: -0.1700
Data Index: 8422092 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5906. Min Act: -0.1700
Data Index: 8708835 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.6219. Min Act: -0.1700
Data Index: 5863051 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5906. Min Act: -0.1700
Data Index: 6776107 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5281. Min Act: -0.1700
Data Index: 599470 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5594. Min Act: -0.1700
Data Index: 3488716 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5281. Min Act: -0.1700
Data Index: 1773740 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5594. Min Act: -0.1700
Data Index: 1657996 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5281. Min Act: -0.1700
Data Index: 1824233 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4969. Min Act: -0.1700
Data Index: 4718831 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4969. Min Act: -0.1700
Data Index: 1486500 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.5281. Min Act: -0.1700
Data Index: 7343071 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 7515829 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 1359478 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 3631121 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 6822473 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4656. Min Act: -0.1700
Data Index: 631524 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7156. Min Range: -5.7156
Max Act: 5.4344. Min Act: -0.1700
Data Index: 3550541 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19