Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.5368. Min Act: -0.1699
Data Index: 5299999 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.5206. Min Act: -0.1700
Data Index: 7880085 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.5045. Min Act: -0.1698
Data Index: 2838677 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4720. Min Act: -0.1700
Data Index: 1261975 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4558. Min Act: -0.1700
Data Index: 7744767 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4395. Min Act: -0.1700
Data Index: 4513472 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4395. Min Act: -0.1679
Data Index: 2227034 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4069. Min Act: -0.1676
Data Index: 3235841 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4232. Min Act: -0.1669
Data Index: 743368 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4232. Min Act: -0.1698
Data Index: 3506495 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4395. Min Act: -0.1699
Data Index: 8223236 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4232. Min Act: -0.1700
Data Index: 4404549 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4232. Min Act: -0.1682
Data Index: 1442363 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.3906. Min Act: -0.1699
Data Index: 3972783 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.3906. Min Act: -0.1685
Data Index: 4208347 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4069. Min Act: -0.1698
Data Index: 5696071 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.3906. Min Act: -0.1700
Data Index: 7517191 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.3906. Min Act: -0.1700
Data Index: 1775483 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.3906. Min Act: -0.1699
Data Index: 3373351 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5368. Min Range: -2.5368
Max Act: 2.4069. Min Act: -0.1700
Data Index: 3146980 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19