Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.6851. Min Act: -0.1700
Data Index: 11934 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.6538. Min Act: -0.1700
Data Index: 8459712 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.6226. Min Act: -0.1700
Data Index: 4921873 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5913. Min Act: -0.1700
Data Index: 2980162 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5913. Min Act: -0.1700
Data Index: 4233201 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5288. Min Act: -0.1700
Data Index: 4110891 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5288. Min Act: -0.1700
Data Index: 3466907 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.5288. Min Act: -0.1700
Data Index: 6406938 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4976. Min Act: -0.1700
Data Index: 8755332 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4976. Min Act: -0.1700
Data Index: 878688 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4976. Min Act: -0.1700
Data Index: 1821627 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4663. Min Act: -0.1700
Data Index: 3711848 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4351. Min Act: -0.1700
Data Index: 778632 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4351. Min Act: -0.1700
Data Index: 1603887 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.4038. Min Act: -0.1700
Data Index: 3475836 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.3726. Min Act: -0.1700
Data Index: 2968166 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.3726. Min Act: -0.1700
Data Index: 2821067 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.3726. Min Act: -0.1700
Data Index: 5535543 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.3413. Min Act: -0.1700
Data Index: 6795039 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6851. Min Range: -5.6851
Max Act: 5.3413. Min Act: -0.1700
Data Index: 4716902 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19