Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.5435. Min Range: -13.5435
Max Act: 13.5435. Min Act: -0.1700
Data Index: 505914 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.5435. Min Range: -13.5435
Max Act: 13.5435. Min Act: -0.1700
Data Index: 6772887 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.5435. Min Range: -13.5435
Max Act: 13.0435. Min Act: -0.1700
Data Index: 2575062 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.2935. Min Act: -0.1700
Data Index: 8759493 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.2310. Min Act: -0.1700
Data Index: 505912 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1685. Min Act: -0.1700
Data Index: 2531867 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1685. Min Act: -0.1700
Data Index: 607586 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1685. Min Act: -0.1700
Data Index: 8687108 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1060. Min Act: -0.1700
Data Index: 3464328 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1060. Min Act: -0.1700
Data Index: 8560626 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1685. Min Act: -0.1700
Data Index: 7365136 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.1060. Min Act: -0.1700
Data Index: 4398942 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.0435. Min Act: -0.1700
Data Index: 8636037 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.5435. Min Range: -13.5435
Max Act: 12.0435. Min Act: -0.1700
Data Index: 7102841 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.5435. Min Range: -13.5435
Max Act: 11.9185. Min Act: -0.1700
Data Index: 1549067 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.5435. Min Range: -13.5435
Max Act: 11.9810. Min Act: -0.1700
Data Index: 6588352 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.5435. Min Range: -13.5435
Max Act: 11.9810. Min Act: -0.1700
Data Index: 7521888 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.5435. Min Range: -13.5435
Max Act: 11.9185. Min Act: -0.1700
Data Index: 4210497 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.5435. Min Range: -13.5435
Max Act: 11.8560. Min Act: -0.1700
Data Index: 5876133 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.5435. Min Range: -13.5435
Max Act: 11.8560. Min Act: -0.1700
Data Index: 8636038 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19