Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.9299. Min Act: -0.1700
Data Index: 2392087 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.8362. Min Act: -0.1700
Data Index: 1228352 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.8674. Min Act: -0.1700
Data Index: 7212843 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.8362. Min Act: -0.1700
Data Index: 5397969 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.8362. Min Act: -0.1700
Data Index: 1228354 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.8362. Min Act: -0.1700
Data Index: 4141238 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.7737. Min Act: -0.1700
Data Index: 1513995 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.7424. Min Act: -0.1700
Data Index: 2228889 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.7112. Min Act: -0.1700
Data Index: 7273545 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.6799. Min Act: -0.1700
Data Index: 1418343 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.6799. Min Act: -0.1700
Data Index: 7134839 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.6487. Min Act: -0.1700
Data Index: 1682226 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.6487. Min Act: -0.1700
Data Index: 4301368 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.6174. Min Act: -0.1700
Data Index: 5078408 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.6174. Min Act: -0.1700
Data Index: 7814684 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.5862. Min Act: -0.1700
Data Index: 8062248 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.5862. Min Act: -0.1700
Data Index: 5842793 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.5862. Min Act: -0.1700
Data Index: 5610393 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.5237. Min Act: -0.1700
Data Index: 2114449 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9299. Min Range: -5.9299
Max Act: 5.5549. Min Act: -0.1700
Data Index: 7387582 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19