Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3620 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.9449. Min Act: -0.1699
Data Index: 3501911 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.9449. Min Act: -0.1700
Data Index: 8174986 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.9136. Min Act: -0.1700
Data Index: 8066120 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.9136. Min Act: -0.1700
Data Index: 5943756 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8824. Min Act: -0.1700
Data Index: 966920 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8824. Min Act: -0.1700
Data Index: 7994983 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8511. Min Act: -0.1700
Data Index: 4460195 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8511. Min Act: -0.1700
Data Index: 8330087 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8511. Min Act: -0.1700
Data Index: 482192 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8199. Min Act: -0.1700
Data Index: 4996856 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8511. Min Act: -0.1700
Data Index: 6320863 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8511. Min Act: -0.1700
Data Index: 6016865 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8199. Min Act: -0.1700
Data Index: 5674790 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8199. Min Act: -0.1700
Data Index: 2674815 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8199. Min Act: -0.1700
Data Index: 4141145 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.7886. Min Act: -0.1700
Data Index: 2559482 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.7886. Min Act: -0.1700
Data Index: 3467788 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8199. Min Act: -0.1700
Data Index: 1332012 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.8199. Min Act: -0.1700
Data Index: 4141013 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9449. Min Range: -6.9449
Max Act: 6.7886. Min Act: -0.1700
Data Index: 5067182 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19