Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1252. Min Range: -7.1252
Max Act: 7.1252. Min Act: -0.1700
Data Index: 7933013 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.9690. Min Act: -0.1700
Data Index: 1829003 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.8127. Min Act: -0.1700
Data Index: 2329568 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.8127. Min Act: -0.1700
Data Index: 8280901 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.6877. Min Act: -0.1700
Data Index: 6503130 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.6565. Min Act: -0.1700
Data Index: 4533010 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.6252. Min Act: -0.1700
Data Index: 264834 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.6252. Min Act: -0.1700
Data Index: 1334530 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5940. Min Act: -0.1700
Data Index: 4925326 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5940. Min Act: -0.1700
Data Index: 572754 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5627. Min Act: -0.1700
Data Index: 3082577 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5315. Min Act: -0.1700
Data Index: 304381 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5315. Min Act: -0.1700
Data Index: 5124397 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5002. Min Act: -0.1700
Data Index: 731101 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5002. Min Act: -0.1700
Data Index: 1421261 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5002. Min Act: -0.1700
Data Index: 119669 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.5002. Min Act: -0.1700
Data Index: 658012 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.4377. Min Act: -0.1700
Data Index: 6279022 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.4690. Min Act: -0.1700
Data Index: 7538156 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1252. Min Range: -7.1252
Max Act: 6.4690. Min Act: -0.1700
Data Index: 1048293 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19