Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2215 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0207. Min Range: -3.0207
Max Act: 3.0207. Min Act: -0.1700
Data Index: 7006407 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.7349. Min Act: -0.1700
Data Index: 6677580 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.7029. Min Act: -0.1700
Data Index: 7649333 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.7029. Min Act: -0.1700
Data Index: 6536958 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6869. Min Act: -0.1700
Data Index: 294617 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6709. Min Act: -0.1700
Data Index: 6347478 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6709. Min Act: -0.1700
Data Index: 5364589 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6709. Min Act: -0.1700
Data Index: 4026459 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6709. Min Act: -0.1700
Data Index: 28610 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6548. Min Act: -0.1700
Data Index: 534283 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6709. Min Act: -0.1700
Data Index: 1036817 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6227. Min Act: -0.1700
Data Index: 5786879 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6388. Min Act: -0.1700
Data Index: 3718700 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6388. Min Act: -0.1700
Data Index: 3821779 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6388. Min Act: -0.1700
Data Index: 3932292 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6227. Min Act: -0.1700
Data Index: 3326223 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6227. Min Act: -0.1700
Data Index: 7019397 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6227. Min Act: -0.1700
Data Index: 2577499 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6388. Min Act: -0.1700
Data Index: 6629996 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0207. Min Range: -3.0207
Max Act: 2.6227. Min Act: -0.1700
Data Index: 1341610 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19