Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5555. Min Range: -5.5555
Max Act: 5.5555. Min Act: -0.1700
Data Index: 7243427 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5555. Min Range: -5.5555
Max Act: 5.1805. Min Act: -0.1700
Data Index: 5275806 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5555. Min Range: -5.5555
Max Act: 5.1180. Min Act: -0.1700
Data Index: 499128 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.9930. Min Act: -0.1700
Data Index: 5615430 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8680. Min Act: -0.1700
Data Index: 8191504 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8367. Min Act: -0.1700
Data Index: 2220314 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8367. Min Act: -0.1700
Data Index: 7162019 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8055. Min Act: -0.1700
Data Index: 5163773 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.7742. Min Act: -0.1700
Data Index: 984530 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8055. Min Act: -0.1700
Data Index: 1554085 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8055. Min Act: -0.1700
Data Index: 3202748 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.8055. Min Act: -0.1700
Data Index: 8339343 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.7742. Min Act: -0.1700
Data Index: 7079551 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.7742. Min Act: -0.1700
Data Index: 2919023 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.6805. Min Act: -0.1700
Data Index: 260224 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.6805. Min Act: -0.1700
Data Index: 2725603 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.6492. Min Act: -0.1700
Data Index: 3058874 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.6492. Min Act: -0.1700
Data Index: 4885085 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.6492. Min Act: -0.1700
Data Index: 3207948 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5555. Min Range: -5.5555
Max Act: 4.6492. Min Act: -0.1700
Data Index: 7483774 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19