Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 836 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.3874. Min Act: -0.1700
Data Index: 6857028 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.3249. Min Act: -0.1700
Data Index: 1994320 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.1061. Min Act: -0.1700
Data Index: 1564800 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.0749. Min Act: -0.1700
Data Index: 2226235 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.0749. Min Act: -0.1700
Data Index: 2022931 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.0436. Min Act: -0.1700
Data Index: 1035510 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.0124. Min Act: -0.1700
Data Index: 1111028 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3874. Min Range: -6.3874
Max Act: 6.0124. Min Act: -0.1700
Data Index: 1362752 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.9811. Min Act: -0.1700
Data Index: 4163790 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.9186. Min Act: -0.1700
Data Index: 532648 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8874. Min Act: -0.1700
Data Index: 7712949 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.9186. Min Act: -0.1700
Data Index: 3528418 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.9186. Min Act: -0.1700
Data Index: 1721020 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8874. Min Act: -0.1700
Data Index: 6957857 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8561. Min Act: -0.1700
Data Index: 2195635 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8561. Min Act: -0.1700
Data Index: 5170604 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8561. Min Act: -0.1700
Data Index: 829706 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8561. Min Act: -0.1700
Data Index: 2456683 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.7936. Min Act: -0.1700
Data Index: 85418 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3874. Min Range: -6.3874
Max Act: 5.8561. Min Act: -0.1700
Data Index: 2106687 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19