Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5466 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4747. Min Range: -7.4747
Max Act: 7.4747. Min Act: -0.1700
Data Index: 5209924 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4747. Min Range: -7.4747
Max Act: 7.0685. Min Act: -0.1700
Data Index: 1114755 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4747. Min Range: -7.4747
Max Act: 7.0372. Min Act: -0.1700
Data Index: 4928527 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.9747. Min Act: -0.1700
Data Index: 6017693 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.9122. Min Act: -0.1700
Data Index: 627360 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.9122. Min Act: -0.1700
Data Index: 7374425 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7872. Min Act: -0.1700
Data Index: 3166748 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7872. Min Act: -0.1700
Data Index: 2475649 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7872. Min Act: -0.1700
Data Index: 1851631 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7560. Min Act: -0.1700
Data Index: 8236065 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7560. Min Act: -0.1700
Data Index: 3969071 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7560. Min Act: -0.1700
Data Index: 5241978 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7247. Min Act: -0.1700
Data Index: 6992365 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.7560. Min Act: -0.1700
Data Index: 8638421 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.6935. Min Act: -0.1700
Data Index: 1885156 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.6935. Min Act: -0.1700
Data Index: 5723479 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.6622. Min Act: -0.1700
Data Index: 5050745 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.6622. Min Act: -0.1700
Data Index: 3767010 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.6935. Min Act: -0.1700
Data Index: 5361131 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4747. Min Range: -7.4747
Max Act: 6.6622. Min Act: -0.1700
Data Index: 6991307 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19