Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2587 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2358. Min Range: -8.2358
Max Act: 8.2358. Min Act: -0.1700
Data Index: 4540536 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2358. Min Range: -8.2358
Max Act: 8.1733. Min Act: -0.1700
Data Index: 1300634 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2358. Min Range: -8.2358
Max Act: 8.2358. Min Act: -0.1700
Data Index: 6766527 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.8608. Min Act: -0.1700
Data Index: 6384876 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.8608. Min Act: -0.1700
Data Index: 885425 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.8608. Min Act: -0.1700
Data Index: 2628569 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.8608. Min Act: -0.1700
Data Index: 3824279 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.6733. Min Act: -0.1700
Data Index: 1917729 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.7358. Min Act: -0.1700
Data Index: 591578 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.6733. Min Act: -0.1700
Data Index: 6285297 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.6733. Min Act: -0.1700
Data Index: 4288923 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.6108. Min Act: -0.1700
Data Index: 6756377 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.6108. Min Act: -0.1700
Data Index: 1147208 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.5483. Min Act: -0.1700
Data Index: 385846 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.5483. Min Act: -0.1700
Data Index: 7746803 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.5483. Min Act: -0.1700
Data Index: 2955046 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.4858. Min Act: -0.1700
Data Index: 7504591 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.5483. Min Act: -0.1700
Data Index: 8643199 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.5483. Min Act: -0.1700
Data Index: 4053198 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2358. Min Range: -8.2358
Max Act: 7.4858. Min Act: -0.1700
Data Index: 5361001 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19