Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5327 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0027. Min Range: -6.0027
Max Act: 6.0027. Min Act: -0.1700
Data Index: 6886933 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.8777. Min Act: -0.1700
Data Index: 5538101 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6902. Min Act: -0.1700
Data Index: 87662 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6902. Min Act: -0.1700
Data Index: 4487183 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6590. Min Act: -0.1700
Data Index: 1176673 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6590. Min Act: -0.1700
Data Index: 6400231 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6277. Min Act: -0.1700
Data Index: 4027848 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6590. Min Act: -0.1700
Data Index: 4936185 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.6277. Min Act: -0.1700
Data Index: 6255909 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.5340. Min Act: -0.1700
Data Index: 3946889 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.5340. Min Act: -0.1700
Data Index: 4088247 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.5652. Min Act: -0.1700
Data Index: 8658074 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.5340. Min Act: -0.1700
Data Index: 6302507 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.5027. Min Act: -0.1700
Data Index: 7223005 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.4715. Min Act: -0.1700
Data Index: 5068394 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.4715. Min Act: -0.1700
Data Index: 1900752 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6877891 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.4715. Min Act: -0.1700
Data Index: 5810089 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.4715. Min Act: -0.1700
Data Index: 978275 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0027. Min Range: -6.0027
Max Act: 5.4715. Min Act: -0.1700
Data Index: 7930407 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19