Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3280 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.1852. Min Act: -0.1700
Data Index: 315651 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.1539. Min Act: -0.1700
Data Index: 5559188 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.1227. Min Act: -0.1700
Data Index: 2869843 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.1227. Min Act: -0.1700
Data Index: 7053918 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.0914. Min Act: -0.1700
Data Index: 1570087 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.1227. Min Act: -0.1700
Data Index: 4155443 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.0289. Min Act: -0.1700
Data Index: 643852 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1852. Min Range: -4.1852
Max Act: 4.0602. Min Act: -0.1700
Data Index: 8787328 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9976. Min Act: -0.1700
Data Index: 2663003 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9976. Min Act: -0.1700
Data Index: 600326 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9976. Min Act: -0.1700
Data Index: 80897 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9976. Min Act: -0.1700
Data Index: 5886870 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9664. Min Act: -0.1700
Data Index: 1735460 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9664. Min Act: -0.1700
Data Index: 3513865 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9664. Min Act: -0.1700
Data Index: 8610310 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9664. Min Act: -0.1700
Data Index: 6663678 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9664. Min Act: -0.1700
Data Index: 3281737 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9351. Min Act: -0.1700
Data Index: 4651068 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9351. Min Act: -0.1700
Data Index: 7073251 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1852. Min Range: -4.1852
Max Act: 3.9351. Min Act: -0.1700
Data Index: 2938352 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19