Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.9779. Min Act: -0.1700
Data Index: 5639323 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.7592. Min Act: -0.1700
Data Index: 5709404 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.7279. Min Act: -0.1700
Data Index: 2164810 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6967. Min Act: -0.1700
Data Index: 3183603 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6654. Min Act: -0.1700
Data Index: 8262783 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6967. Min Act: -0.1700
Data Index: 7637698 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6967. Min Act: -0.1700
Data Index: 3833748 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6342. Min Act: -0.1700
Data Index: 84769 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 6653130 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6654. Min Act: -0.1700
Data Index: 8688805 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6342. Min Act: -0.1700
Data Index: 7501503 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6342. Min Act: -0.1700
Data Index: 1090302 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 5507390 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 1462399 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 5769475 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 3737489 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5717. Min Act: -0.1700
Data Index: 2170420 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.6029. Min Act: -0.1700
Data Index: 2706036 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5717. Min Act: -0.1700
Data Index: 6025255 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9779. Min Range: -5.9779
Max Act: 5.5404. Min Act: -0.1700
Data Index: 2075343 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19