Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.8589. Min Act: -0.1700
Data Index: 4758115 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.7651. Min Act: -0.1700
Data Index: 8645752 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.6089. Min Act: -0.1700
Data Index: 8645758 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.6401. Min Act: -0.1700
Data Index: 5304530 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5776. Min Act: -0.1700
Data Index: 8221302 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5464. Min Act: -0.1700
Data Index: 3856861 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.6089. Min Act: -0.1700
Data Index: 6298760 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5776. Min Act: -0.1700
Data Index: 6333054 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5464. Min Act: -0.1700
Data Index: 1820712 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5464. Min Act: -0.1700
Data Index: 2275267 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5151. Min Act: -0.1700
Data Index: 5281858 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5151. Min Act: -0.1700
Data Index: 1746337 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.5151. Min Act: -0.1700
Data Index: 2200905 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4526. Min Act: -0.1700
Data Index: 1128657 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4839. Min Act: -0.1700
Data Index: 2187759 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4214. Min Act: -0.1700
Data Index: 5407482 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4214. Min Act: -0.1700
Data Index: 49383 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4526. Min Act: -0.1700
Data Index: 4407555 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4526. Min Act: -0.1700
Data Index: 7478440 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8589. Min Range: -6.8589
Max Act: 6.4214. Min Act: -0.1700
Data Index: 511027 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19