Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.9123. Min Act: -0.1700
Data Index: 2111578 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.8186. Min Act: -0.1700
Data Index: 3329707 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.8498. Min Act: -0.1700
Data Index: 3951596 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.7561. Min Act: -0.1700
Data Index: 2697800 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.7248. Min Act: -0.1700
Data Index: 8031626 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.6311. Min Act: -0.1700
Data Index: 7753808 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.5686. Min Act: -0.1700
Data Index: 3978196 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.5373. Min Act: -0.1700
Data Index: 6327977 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.5373. Min Act: -0.1700
Data Index: 8700601 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.5061. Min Act: -0.1700
Data Index: 6309818 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.4748. Min Act: -0.1700
Data Index: 8499864 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.4748. Min Act: -0.1700
Data Index: 4177873 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.4436. Min Act: -0.1700
Data Index: 1255905 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.3811. Min Act: -0.1700
Data Index: 6470031 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.4123. Min Act: -0.1700
Data Index: 883690 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.3811. Min Act: -0.1700
Data Index: 7421692 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.4436. Min Act: -0.1700
Data Index: 7986906 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.3811. Min Act: -0.1700
Data Index: 4887752 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.2873. Min Act: -0.1700
Data Index: 25412 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9123. Min Range: -7.9123
Max Act: 7.3186. Min Act: -0.1700
Data Index: 3032019 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19