Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3180. Min Range: -9.3180
Max Act: 9.3180. Min Act: -0.1700
Data Index: 1065783 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3180. Min Range: -9.3180
Max Act: 9.2555. Min Act: -0.1700
Data Index: 5375430 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.8180. Min Act: -0.1700
Data Index: 8209844 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.6305. Min Act: -0.1700
Data Index: 552693 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.6305. Min Act: -0.1700
Data Index: 4727136 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.5055. Min Act: -0.1700
Data Index: 3973639 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.3805. Min Act: -0.1700
Data Index: 83452 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.3805. Min Act: -0.1700
Data Index: 6218509 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.3805. Min Act: -0.1700
Data Index: 7018980 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.3180. Min Act: -0.1700
Data Index: 487742 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.3180. Min Act: -0.1700
Data Index: 928938 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.2555. Min Act: -0.1700
Data Index: 6017880 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.2555. Min Act: -0.1700
Data Index: 7293666 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.1930. Min Act: -0.1700
Data Index: 1279753 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.1305. Min Act: -0.1700
Data Index: 554384 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.0680. Min Act: -0.1700
Data Index: 4727120 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.0680. Min Act: -0.1700
Data Index: 4284921 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.0055. Min Act: -0.1700
Data Index: 4169205 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.0055. Min Act: -0.1700
Data Index: 6218508 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3180. Min Range: -9.3180
Max Act: 8.0680. Min Act: -0.1700
Data Index: 8241645 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19