Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2408 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0966. Min Range: -6.0966
Max Act: 6.0966. Min Act: -0.1700
Data Index: 6980812 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.9716. Min Act: -0.1700
Data Index: 8576473 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.7841. Min Act: -0.1700
Data Index: 739785 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.7216. Min Act: -0.1700
Data Index: 7944524 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.7216. Min Act: -0.1700
Data Index: 3812391 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.6591. Min Act: -0.1700
Data Index: 1246761 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.6278. Min Act: -0.1700
Data Index: 3255286 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.6278. Min Act: -0.1700
Data Index: 6025395 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.6591. Min Act: -0.1700
Data Index: 2574320 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5966. Min Act: -0.1700
Data Index: 5206165 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5653. Min Act: -0.1700
Data Index: 5100399 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5966. Min Act: -0.1700
Data Index: 7832060 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5653. Min Act: -0.1700
Data Index: 213879 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5653. Min Act: -0.1700
Data Index: 4119140 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5653. Min Act: -0.1700
Data Index: 5037134 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5341. Min Act: -0.1700
Data Index: 7910349 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5341. Min Act: -0.1700
Data Index: 2827926 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5341. Min Act: -0.1700
Data Index: 2945444 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5341. Min Act: -0.1700
Data Index: 2307635 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0966. Min Range: -6.0966
Max Act: 5.5028. Min Act: -0.1700
Data Index: 838464 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19