Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6036 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6760. Min Range: -7.6760
Max Act: 7.6760. Min Act: -0.1700
Data Index: 7986822 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6760. Min Range: -7.6760
Max Act: 7.0197. Min Act: -0.1700
Data Index: 8405226 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.9572. Min Act: -0.1700
Data Index: 6443738 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.9572. Min Act: -0.1700
Data Index: 1121303 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.8322. Min Act: -0.1700
Data Index: 1140423 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.8010. Min Act: -0.1700
Data Index: 5112643 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.8322. Min Act: -0.1700
Data Index: 5727260 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.8010. Min Act: -0.1700
Data Index: 4207437 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.7697. Min Act: -0.1700
Data Index: 2107844 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.7697. Min Act: -0.1700
Data Index: 123223 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.7385. Min Act: -0.1700
Data Index: 2738725 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.7072. Min Act: -0.1700
Data Index: 6866823 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.6447. Min Act: -0.1700
Data Index: 3781058 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.7072. Min Act: -0.1700
Data Index: 5492302 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.6135. Min Act: -0.1700
Data Index: 3860129 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.6447. Min Act: -0.1700
Data Index: 1519553 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.6135. Min Act: -0.1700
Data Index: 5706526 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.6135. Min Act: -0.1700
Data Index: 8588288 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.5510. Min Act: -0.1700
Data Index: 2131447 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6760. Min Range: -7.6760
Max Act: 6.5197. Min Act: -0.1700
Data Index: 5853660 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19