Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4098 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2818. Min Range: -9.2818
Max Act: 9.2818. Min Act: -0.1700
Data Index: 3256694 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2818. Min Range: -9.2818
Max Act: 9.2193. Min Act: -0.1700
Data Index: 2269339 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2818. Min Range: -9.2818
Max Act: 9.1568. Min Act: -0.1700
Data Index: 2839382 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2818. Min Range: -9.2818
Max Act: 9.0943. Min Act: -0.1700
Data Index: 3898810 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.9693. Min Act: -0.1700
Data Index: 4994165 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.8443. Min Act: -0.1700
Data Index: 4680098 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.7818. Min Act: -0.1700
Data Index: 6724503 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.7818. Min Act: -0.1700
Data Index: 2265613 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.7193. Min Act: -0.1700
Data Index: 3985474 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.6568. Min Act: -0.1700
Data Index: 1246979 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.7193. Min Act: -0.1700
Data Index: 4713910 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.7193. Min Act: -0.1700
Data Index: 4023633 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.6568. Min Act: -0.1700
Data Index: 5475257 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.6568. Min Act: -0.1700
Data Index: 313388 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.6568. Min Act: -0.1700
Data Index: 3864992 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.6568. Min Act: -0.1700
Data Index: 3717279 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.5943. Min Act: -0.1700
Data Index: 7774352 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.6568. Min Act: -0.1700
Data Index: 3551953 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.5943. Min Act: -0.1700
Data Index: 2382760 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2818. Min Range: -9.2818
Max Act: 8.5943. Min Act: -0.1700
Data Index: 4704872 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19