Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 39 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3995. Min Range: -7.3995
Max Act: 7.3995. Min Act: -0.1700
Data Index: 901112 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3995. Min Range: -7.3995
Max Act: 7.2745. Min Act: -0.1700
Data Index: 3649350 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3995. Min Range: -7.3995
Max Act: 7.1182. Min Act: -0.1700
Data Index: 1707953 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3995. Min Range: -7.3995
Max Act: 7.0870. Min Act: -0.1700
Data Index: 837913 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3995. Min Range: -7.3995
Max Act: 7.0245. Min Act: -0.1700
Data Index: 5412054 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.9932. Min Act: -0.1700
Data Index: 4155456 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.9620. Min Act: -0.1700
Data Index: 4622637 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.9620. Min Act: -0.1700
Data Index: 6359583 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.9307. Min Act: -0.1700
Data Index: 4593698 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.8995. Min Act: -0.1700
Data Index: 2656395 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.8995. Min Act: -0.1700
Data Index: 4529764 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.8682. Min Act: -0.1700
Data Index: 6961021 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.8370. Min Act: -0.1700
Data Index: 774393 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.8057. Min Act: -0.1700
Data Index: 5082665 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.8057. Min Act: -0.1700
Data Index: 7387068 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.7745. Min Act: -0.1700
Data Index: 6404074 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.7745. Min Act: -0.1700
Data Index: 6546796 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.7432. Min Act: -0.1700
Data Index: 5916761 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.7432. Min Act: -0.1700
Data Index: 1203999 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3995. Min Range: -7.3995
Max Act: 6.7432. Min Act: -0.1700
Data Index: 5921671 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19