Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.9226. Min Act: -0.1700
Data Index: 7642899 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.7351. Min Act: -0.1700
Data Index: 4296881 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.6726. Min Act: -0.1700
Data Index: 4296880 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.6414. Min Act: -0.1700
Data Index: 8223663 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.6101. Min Act: -0.1700
Data Index: 8223662 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.5476. Min Act: -0.1699
Data Index: 3539039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.5476. Min Act: -0.1700
Data Index: 5938864 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.5476. Min Act: -0.1700
Data Index: 6375928 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.4851. Min Act: -0.1700
Data Index: 6852946 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.4539. Min Act: -0.1700
Data Index: 5811729 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.4539. Min Act: -0.1700
Data Index: 402762 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.4226. Min Act: -0.1700
Data Index: 892269 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.4539. Min Act: -0.1700
Data Index: 2916709 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.3914. Min Act: -0.1700
Data Index: 3614237 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.3914. Min Act: -0.1700
Data Index: 2916711 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.3914. Min Act: -0.1700
Data Index: 8543243 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.4226. Min Act: -0.1700
Data Index: 3511061 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.3601. Min Act: -0.1700
Data Index: 2917122 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.3601. Min Act: -0.1700
Data Index: 4415626 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9226. Min Range: -4.9226
Max Act: 4.3601. Min Act: -0.1700
Data Index: 6310908 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19