Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.9055. Min Act: -0.1700
Data Index: 6395610 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.8743. Min Act: -0.1700
Data Index: 1551724 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.8430. Min Act: -0.1700
Data Index: 5533557 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.7805. Min Act: -0.1700
Data Index: 4604375 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.7805. Min Act: -0.1700
Data Index: 6246224 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.7493. Min Act: -0.1700
Data Index: 6002899 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.7493. Min Act: -0.1700
Data Index: 855787 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.7493. Min Act: -0.1700
Data Index: 8741328 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.6868. Min Act: -0.1700
Data Index: 4612845 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.6868. Min Act: -0.1700
Data Index: 3384187 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.6555. Min Act: -0.1700
Data Index: 2502272 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.6555. Min Act: -0.1700
Data Index: 7967163 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.6243. Min Act: -0.1700
Data Index: 694361 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.6243. Min Act: -0.1700
Data Index: 1531590 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.5930. Min Act: -0.1700
Data Index: 1750779 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.5930. Min Act: -0.1700
Data Index: 8277379 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.5930. Min Act: -0.1700
Data Index: 4188628 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.5618. Min Act: -0.1700
Data Index: 1316929 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.5618. Min Act: -0.1700
Data Index: 4799464 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9055. Min Range: -5.9055
Max Act: 5.5618. Min Act: -0.1700
Data Index: 2281800 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19