Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.4188. Min Act: -0.1700
Data Index: 4344523 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.3875. Min Act: -0.1700
Data Index: 7732051 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.3250. Min Act: -0.1700
Data Index: 1353623 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.2625. Min Act: -0.1700
Data Index: 4215718 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.2313. Min Act: -0.1700
Data Index: 1353612 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.2313. Min Act: -0.1700
Data Index: 6477783 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.2000. Min Act: -0.1700
Data Index: 7536690 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1688. Min Act: -0.1700
Data Index: 2722024 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1688. Min Act: -0.1700
Data Index: 2021239 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1375. Min Act: -0.1700
Data Index: 510379 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2269220 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1688. Min Act: -0.1700
Data Index: 243890 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1375. Min Act: -0.1700
Data Index: 2588138 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1063. Min Act: -0.1700
Data Index: 5028304 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1063. Min Act: -0.1700
Data Index: 5604376 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1063. Min Act: -0.1700
Data Index: 4318140 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1063. Min Act: -0.1700
Data Index: 6217411 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.1063. Min Act: -0.1700
Data Index: 23291 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.0750. Min Act: -0.1700
Data Index: 1351598 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4188. Min Range: -5.4188
Max Act: 5.0438. Min Act: -0.1700
Data Index: 3166984 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19