Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5894. Min Act: -0.1700
Data Index: 2511860 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5894. Min Act: -0.1700
Data Index: 6632161 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5894. Min Act: -0.1700
Data Index: 8217373 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5894. Min Act: -0.1700
Data Index: 877846 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5581. Min Act: -0.1700
Data Index: 4188875 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5581. Min Act: -0.1700
Data Index: 3402106 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5581. Min Act: -0.1700
Data Index: 7464852 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5581. Min Act: -0.1700
Data Index: 1954193 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5581. Min Act: -0.1700
Data Index: 865733 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5581. Min Act: -0.1700
Data Index: 3869531 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 4045713 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 6528398 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 6853914 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 1403967 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 4033111 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 3869529 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.5268. Min Act: -0.1700
Data Index: 8705233 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.4955. Min Act: -0.1700
Data Index: 5957032 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.4955. Min Act: -0.1700
Data Index: 6068524 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5894. Min Range: -3.5894
Max Act: 3.4955. Min Act: -0.1700
Data Index: 6205659 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19