Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 287 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.6908. Min Act: -0.1697
Data Index: 511600 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.6665. Min Act: -0.1700
Data Index: 2306905 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.6264. Min Act: -0.1699
Data Index: 7364410 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5948. Min Act: -0.1698
Data Index: 842523 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5791. Min Act: -0.1700
Data Index: 4235564 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5714. Min Act: -0.1700
Data Index: 6862480 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5791. Min Act: -0.1700
Data Index: 5778370 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5636. Min Act: -0.1700
Data Index: 670883 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5559. Min Act: -0.1700
Data Index: 113647 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5482. Min Act: -0.1700
Data Index: 1695953 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5482. Min Act: -0.1700
Data Index: 2042572 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5405. Min Act: -0.1700
Data Index: 6377752 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5328. Min Act: -0.1700
Data Index: 8653175 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5328. Min Act: -0.1700
Data Index: 3879185 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5252. Min Act: -0.1700
Data Index: 6476973 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5252. Min Act: -0.1685
Data Index: 7789834 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5176. Min Act: -0.1699
Data Index: 8417433 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5176. Min Act: -0.1700
Data Index: 3142100 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5100. Min Act: -0.1700
Data Index: 3080491 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6908. Min Range: -0.6908
Max Act: 0.5100. Min Act: -0.1700
Data Index: 1812567 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19