Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5431 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9380. Min Act: -0.1700
Data Index: 4327478 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.9067. Min Act: -0.1700
Data Index: 8147001 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8755. Min Act: -0.1700
Data Index: 5611377 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8755. Min Act: -0.1700
Data Index: 977627 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8130. Min Act: -0.1700
Data Index: 2793985 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8442. Min Act: -0.1700
Data Index: 4736197 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1599519 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.8130. Min Act: -0.1700
Data Index: 5611506 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7505. Min Act: -0.1700
Data Index: 3823204 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.7505. Min Act: -0.1700
Data Index: 7838502 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6880. Min Act: -0.1700
Data Index: 7044838 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6255. Min Act: -0.1700
Data Index: 5791069 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6567. Min Act: -0.1700
Data Index: 1856979 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.6255. Min Act: -0.1700
Data Index: 4081778 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5630. Min Act: -0.1700
Data Index: 7082120 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5630. Min Act: -0.1700
Data Index: 7206886 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5630. Min Act: -0.1700
Data Index: 2269990 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5317. Min Act: -0.1700
Data Index: 6119184 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5317. Min Act: -0.1700
Data Index: 6284740 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9380. Min Range: -4.9380
Max Act: 4.5005. Min Act: -0.1700
Data Index: 5468332 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19