Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4564 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.8209. Min Act: -0.1700
Data Index: 1888725 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.7584. Min Act: -0.1700
Data Index: 2960245 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.7271. Min Act: -0.1700
Data Index: 6425176 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6801. Min Act: -0.1700
Data Index: 8691335 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6645. Min Act: -0.1700
Data Index: 2975180 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6489. Min Act: -0.1700
Data Index: 6897175 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6645. Min Act: -0.1700
Data Index: 7437052 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6489. Min Act: -0.1700
Data Index: 5341348 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6332. Min Act: -0.1700
Data Index: 4580586 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6489. Min Act: -0.1700
Data Index: 3007319 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6332. Min Act: -0.1700
Data Index: 8548328 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6489. Min Act: -0.1700
Data Index: 53658 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6176. Min Act: -0.1700
Data Index: 4860286 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.6019. Min Act: -0.1700
Data Index: 8313906 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.5706. Min Act: -0.1700
Data Index: 3958214 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.5706. Min Act: -0.1700
Data Index: 8544247 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.5706. Min Act: -0.1700
Data Index: 952840 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.5549. Min Act: -0.1700
Data Index: 3468395 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.5549. Min Act: -0.1700
Data Index: 752713 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8209. Min Range: -3.8209
Max Act: 3.5549. Min Act: -0.1700
Data Index: 6344770 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19