Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2624 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.4979. Min Act: -0.1700
Data Index: 1489714 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.4979. Min Act: -0.1700
Data Index: 594246 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.3729. Min Act: -0.1700
Data Index: 8748882 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.3104. Min Act: -0.1700
Data Index: 868548 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.1854. Min Act: -0.1700
Data Index: 7707387 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.1229. Min Act: -0.1700
Data Index: 3120562 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.0604. Min Act: -0.1700
Data Index: 2215891 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 6349450 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 4952286 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4979. Min Range: -8.4979
Max Act: 8.0604. Min Act: -0.1700
Data Index: 8496034 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 2109926 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 2638431 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9979. Min Act: -0.1700
Data Index: 4540103 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9354. Min Act: -0.1700
Data Index: 7349692 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 7450907 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.9354. Min Act: -0.1700
Data Index: 6446950 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 7155637 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 1586131 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 776083 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4979. Min Range: -8.4979
Max Act: 7.8729. Min Act: -0.1700
Data Index: 3410669 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19