Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5763 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1731. Min Range: -6.1731
Max Act: 6.1731. Min Act: -0.1700
Data Index: 6842251 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1731. Min Range: -6.1731
Max Act: 6.1418. Min Act: -0.1700
Data Index: 464742 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1731. Min Range: -6.1731
Max Act: 6.1106. Min Act: -0.1700
Data Index: 277281 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1731. Min Range: -6.1731
Max Act: 6.0793. Min Act: -0.1700
Data Index: 2014102 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.9231. Min Act: -0.1700
Data Index: 1297034 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8918. Min Act: -0.1700
Data Index: 5734437 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8606. Min Act: -0.1700
Data Index: 961605 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8606. Min Act: -0.1700
Data Index: 4149360 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8606. Min Act: -0.1700
Data Index: 7486787 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8293. Min Act: -0.1700
Data Index: 1617450 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3751565 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.8606. Min Act: -0.1700
Data Index: 1923450 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7981. Min Act: -0.1700
Data Index: 4637902 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7981. Min Act: -0.1700
Data Index: 350006 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7668. Min Act: -0.1700
Data Index: 878283 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7668. Min Act: -0.1700
Data Index: 6134243 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7668. Min Act: -0.1700
Data Index: 4792111 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7981. Min Act: -0.1700
Data Index: 3227701 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7356. Min Act: -0.1700
Data Index: 6599156 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1731. Min Range: -6.1731
Max Act: 5.7356. Min Act: -0.1700
Data Index: 464748 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19