Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.6063. Min Act: -0.1700
Data Index: 5725146 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.2313. Min Act: -0.1700
Data Index: 5725147 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.2001. Min Act: -0.1700
Data Index: 7276693 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.2313. Min Act: -0.1700
Data Index: 570393 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.2001. Min Act: -0.1700
Data Index: 2416789 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.1688. Min Act: -0.1700
Data Index: 8137521 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.1376. Min Act: -0.1700
Data Index: 1575605 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.1376. Min Act: -0.1700
Data Index: 3484648 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.1376. Min Act: -0.1700
Data Index: 8315163 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.1063. Min Act: -0.1700
Data Index: 8706989 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0751. Min Act: -0.1700
Data Index: 7408584 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0751. Min Act: -0.1700
Data Index: 802198 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 6691878 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0751. Min Act: -0.1700
Data Index: 2921972 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0438. Min Act: -0.1700
Data Index: 4521647 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0125. Min Act: -0.1697
Data Index: 6723663 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0125. Min Act: -0.1700
Data Index: 5459771 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6063. Min Range: -4.6063
Max Act: 4.0125. Min Act: -0.1700
Data Index: 5818900 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6063. Min Range: -4.6063
Max Act: 3.9813. Min Act: -0.1700
Data Index: 1769327 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6063. Min Range: -4.6063
Max Act: 3.9813. Min Act: -0.1700
Data Index: 7078028 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19