Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.6812. Min Act: -0.1700
Data Index: 4972309 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.6812. Min Act: -0.1700
Data Index: 4270028 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.6812. Min Act: -0.1700
Data Index: 5936457 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.6812. Min Act: -0.1700
Data Index: 7775553 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5875. Min Act: -0.1700
Data Index: 8181952 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5875. Min Act: -0.1700
Data Index: 3128778 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5562. Min Act: -0.1700
Data Index: 1813064 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5875. Min Act: -0.1700
Data Index: 7465098 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5250. Min Act: -0.1700
Data Index: 7554984 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5250. Min Act: -0.1700
Data Index: 5386423 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.5250. Min Act: -0.1700
Data Index: 4858937 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4625. Min Act: -0.1700
Data Index: 4893497 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4625. Min Act: -0.1700
Data Index: 2452676 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4312. Min Act: -0.1700
Data Index: 6169241 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4625. Min Act: -0.1700
Data Index: 4270030 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4312. Min Act: -0.1700
Data Index: 8263343 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4312. Min Act: -0.1700
Data Index: 5785973 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4312. Min Act: -0.1700
Data Index: 4442695 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4312. Min Act: -0.1700
Data Index: 418984 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6812. Min Range: -6.6812
Max Act: 6.4000. Min Act: -0.1700
Data Index: 2597159 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19