Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.8160. Min Act: -0.1700
Data Index: 807520 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.5035. Min Act: -0.1700
Data Index: 6845836 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.4410. Min Act: -0.1700
Data Index: 7319710 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.4410. Min Act: -0.1700
Data Index: 3608783 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.4410. Min Act: -0.1700
Data Index: 4578709 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3785. Min Act: -0.1700
Data Index: 1910571 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3785. Min Act: -0.1700
Data Index: 1944778 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3472. Min Act: -0.1700
Data Index: 1487529 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3472. Min Act: -0.1700
Data Index: 6823719 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.3472. Min Act: -0.1700
Data Index: 8093926 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2847. Min Act: -0.1700
Data Index: 6449092 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2535. Min Act: -0.1700
Data Index: 5352784 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2535. Min Act: -0.1700
Data Index: 2418927 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2847. Min Act: -0.1700
Data Index: 3730446 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2222. Min Act: -0.1700
Data Index: 110954 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2222. Min Act: -0.1700
Data Index: 6014880 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.2535. Min Act: -0.1700
Data Index: 3837381 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 6459980 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 2773817 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8160. Min Range: -5.8160
Max Act: 5.1910. Min Act: -0.1700
Data Index: 5606105 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19