Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.9555. Min Act: -0.1700
Data Index: 6568376 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.8930. Min Act: -0.1700
Data Index: 8114605 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.6430. Min Act: -0.1700
Data Index: 3782954 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.6430. Min Act: -0.1700
Data Index: 1216522 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.6430. Min Act: -0.1700
Data Index: 3734883 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.5805. Min Act: -0.1700
Data Index: 5130884 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.5180. Min Act: -0.1700
Data Index: 5560830 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.4555. Min Act: -0.1700
Data Index: 1973761 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.5180. Min Act: -0.1700
Data Index: 3987217 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.4555. Min Act: -0.1700
Data Index: 936698 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3930. Min Act: -0.1700
Data Index: 1974468 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3930. Min Act: -0.1700
Data Index: 5056759 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3930. Min Act: -0.1700
Data Index: 8782137 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3930. Min Act: -0.1700
Data Index: 1670347 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3930. Min Act: -0.1700
Data Index: 3511189 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3305. Min Act: -0.1700
Data Index: 2907429 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.3305. Min Act: -0.1700
Data Index: 5390560 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.2680. Min Act: -0.1700
Data Index: 6980358 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.2680. Min Act: -0.1700
Data Index: 2779208 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9555. Min Range: -12.9555
Max Act: 12.2680. Min Act: -0.1700
Data Index: 5302538 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19