Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4765 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.5359. Min Act: -0.1700
Data Index: 5930817 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.3484. Min Act: -0.1700
Data Index: 1273438 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.2547. Min Act: -0.1700
Data Index: 8094748 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.2234. Min Act: -0.1700
Data Index: 5526550 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.1922. Min Act: -0.1700
Data Index: 1256391 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0984. Min Act: -0.1700
Data Index: 6773370 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0672. Min Act: -0.1700
Data Index: 172627 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0672. Min Act: -0.1700
Data Index: 5224692 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0672. Min Act: -0.1700
Data Index: 3047276 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0359. Min Act: -0.1700
Data Index: 4183837 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0359. Min Act: -0.1700
Data Index: 791206 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0359. Min Act: -0.1700
Data Index: 3845839 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0047. Min Act: -0.1700
Data Index: 6824986 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0047. Min Act: -0.1700
Data Index: 855995 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5359. Min Range: -6.5359
Max Act: 6.0047. Min Act: -0.1700
Data Index: 1681767 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5359. Min Range: -6.5359
Max Act: 5.9734. Min Act: -0.1700
Data Index: 3640717 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5359. Min Range: -6.5359
Max Act: 5.9734. Min Act: -0.1700
Data Index: 643817 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5359. Min Range: -6.5359
Max Act: 5.9734. Min Act: -0.1700
Data Index: 5644095 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5359. Min Range: -6.5359
Max Act: 5.9422. Min Act: -0.1700
Data Index: 3408957 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5359. Min Range: -6.5359
Max Act: 5.9422. Min Act: -0.1700
Data Index: 4984460 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19