Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3057. Min Range: -6.3057
Max Act: 6.3057. Min Act: -0.1700
Data Index: 3742913 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3057. Min Range: -6.3057
Max Act: 6.2432. Min Act: -0.1700
Data Index: 8185861 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3057. Min Range: -6.3057
Max Act: 6.1494. Min Act: -0.1700
Data Index: 3818728 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3057. Min Range: -6.3057
Max Act: 6.0869. Min Act: -0.1700
Data Index: 3578600 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.9307. Min Act: -0.1700
Data Index: 3742917 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8994. Min Act: -0.1700
Data Index: 283770 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8994. Min Act: -0.1700
Data Index: 8470391 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8682. Min Act: -0.1700
Data Index: 5180057 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8682. Min Act: -0.1700
Data Index: 5215522 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8369. Min Act: -0.1700
Data Index: 3955694 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.7744. Min Act: -0.1700
Data Index: 1176315 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8057. Min Act: -0.1700
Data Index: 523871 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8057. Min Act: -0.1700
Data Index: 152274 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8057. Min Act: -0.1700
Data Index: 6910045 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.8057. Min Act: -0.1700
Data Index: 5610809 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.7744. Min Act: -0.1700
Data Index: 7967981 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.7744. Min Act: -0.1700
Data Index: 2069680 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.7744. Min Act: -0.1700
Data Index: 2062740 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6082656 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3057. Min Range: -6.3057
Max Act: 5.7432. Min Act: -0.1700
Data Index: 4569250 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19