Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6368 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.3826. Min Act: -0.1700
Data Index: 3939724 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3826. Min Range: -7.3826
Max Act: 7.3201. Min Act: -0.1700
Data Index: 7834172 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.9139. Min Act: -0.1700
Data Index: 565966 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.8514. Min Act: -0.1700
Data Index: 6915774 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.7264. Min Act: -0.1700
Data Index: 2830902 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.7264. Min Act: -0.1700
Data Index: 3527696 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.7264. Min Act: -0.1700
Data Index: 7467421 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 3896071 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 7670988 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 1576590 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 6279228 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 4888409 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 525941 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 5139143 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6951. Min Act: -0.1700
Data Index: 5822707 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6639. Min Act: -0.1700
Data Index: 7325071 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6639. Min Act: -0.1700
Data Index: 8316967 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6639. Min Act: -0.1700
Data Index: 84657 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6639. Min Act: -0.1700
Data Index: 5590831 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3826. Min Range: -7.3826
Max Act: 6.6326. Min Act: -0.1700
Data Index: 3175318 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19