Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.5233. Min Act: -0.1700
Data Index: 7888271 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.4608. Min Act: -0.1700
Data Index: 3158282 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.4608. Min Act: -0.1700
Data Index: 787388 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.4608. Min Act: -0.1700
Data Index: 5420585 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.4295. Min Act: -0.1700
Data Index: 4579392 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3983. Min Act: -0.1700
Data Index: 1350578 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3358. Min Act: -0.1700
Data Index: 552412 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3358. Min Act: -0.1700
Data Index: 3390310 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3358. Min Act: -0.1700
Data Index: 1194190 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3358. Min Act: -0.1700
Data Index: 3734224 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3045. Min Act: -0.1700
Data Index: 2147077 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3045. Min Act: -0.1700
Data Index: 4572827 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.3045. Min Act: -0.1700
Data Index: 3669686 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2420. Min Act: -0.1700
Data Index: 8200296 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1940399 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2733. Min Act: -0.1700
Data Index: 5863979 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1987551 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2733. Min Act: -0.1700
Data Index: 1738683 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2733. Min Act: -0.1700
Data Index: 7336728 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5233. Min Range: -6.5233
Max Act: 6.2420. Min Act: -0.1700
Data Index: 6426097 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19