Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 513 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3620. Min Range: -6.3620
Max Act: 6.3620. Min Act: -0.1700
Data Index: 7372991 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3620. Min Range: -6.3620
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6845781 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3620. Min Range: -6.3620
Max Act: 6.2057. Min Act: -0.1700
Data Index: 3604122 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3620. Min Range: -6.3620
Max Act: 6.1120. Min Act: -0.1700
Data Index: 8517870 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3620. Min Range: -6.3620
Max Act: 6.0495. Min Act: -0.1700
Data Index: 6973098 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.9870. Min Act: -0.1700
Data Index: 4298906 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.9557. Min Act: -0.1700
Data Index: 8004812 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.9245. Min Act: -0.1700
Data Index: 5457269 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.9245. Min Act: -0.1700
Data Index: 8521365 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.8932. Min Act: -0.1700
Data Index: 986351 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.8932. Min Act: -0.1700
Data Index: 8677510 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.8620. Min Act: -0.1700
Data Index: 1347158 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.8620. Min Act: -0.1700
Data Index: 993184 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7995. Min Act: -0.1700
Data Index: 3368656 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7995. Min Act: -0.1700
Data Index: 3375932 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7995. Min Act: -0.1700
Data Index: 8303000 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7995. Min Act: -0.1700
Data Index: 3990673 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7682. Min Act: -0.1700
Data Index: 973103 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7682. Min Act: -0.1700
Data Index: 1257608 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3620. Min Range: -6.3620
Max Act: 5.7682. Min Act: -0.1700
Data Index: 7894692 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19