Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 91 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.6750. Min Act: -0.1700
Data Index: 663992 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.6125. Min Act: -0.1700
Data Index: 686907 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3937. Min Act: -0.1700
Data Index: 2846229 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3937. Min Act: -0.1700
Data Index: 3821744 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 2569362 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3625. Min Act: -0.1700
Data Index: 3068993 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3000. Min Act: -0.1700
Data Index: 771730 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3312. Min Act: -0.1700
Data Index: 1453527 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3000. Min Act: -0.1700
Data Index: 3069007 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3000. Min Act: -0.1700
Data Index: 5255993 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3000. Min Act: -0.1700
Data Index: 7025083 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.3000. Min Act: -0.1700
Data Index: 7840350 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2687. Min Act: -0.1700
Data Index: 3782330 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2687. Min Act: -0.1700
Data Index: 4929575 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2687. Min Act: -0.1700
Data Index: 6682131 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2375. Min Act: -0.1700
Data Index: 473914 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2375. Min Act: -0.1700
Data Index: 5652416 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2375. Min Act: -0.1700
Data Index: 1587839 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2375. Min Act: -0.1700
Data Index: 4526254 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6750. Min Range: -4.6750
Max Act: 4.2062. Min Act: -0.1700
Data Index: 1080963 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19