Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.9902. Min Act: -0.1700
Data Index: 3268631 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3154696 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.2714. Min Act: -0.1700
Data Index: 1036942 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 1195060 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 1599649 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.2089. Min Act: -0.1700
Data Index: 456480 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 6248068 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 6494448 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 2843297 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1777. Min Act: -0.1700
Data Index: 7559886 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1464. Min Act: -0.1700
Data Index: 568662 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1464. Min Act: -0.1700
Data Index: 4631094 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.1152. Min Act: -0.1700
Data Index: 3013479 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0839. Min Act: -0.1700
Data Index: 7470946 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0527. Min Act: -0.1700
Data Index: 1645382 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0527. Min Act: -0.1700
Data Index: 5924033 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8484603 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0527. Min Act: -0.1700
Data Index: 8775769 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0214. Min Act: -0.1700
Data Index: 544405 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9902. Min Range: -5.9902
Max Act: 5.0214. Min Act: -0.1700
Data Index: 1782959 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19