Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6048 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0010. Min Range: -5.0010
Max Act: 5.0010. Min Act: -0.1700
Data Index: 123947 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.9073. Min Act: -0.1700
Data Index: 1293105 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 6006272 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8760. Min Act: -0.1700
Data Index: 6720724 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8760. Min Act: -0.1700
Data Index: 8023328 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 8005469 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 7956322 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 319744 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 2818324 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 6435709 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 7246326 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 6810498 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8448. Min Act: -0.1700
Data Index: 4924997 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 7708723 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 6175116 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 2375053 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 1817930 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 1293106 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 6660694 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0010. Min Range: -5.0010
Max Act: 4.8135. Min Act: -0.1700
Data Index: 1970846 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19