Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1103. Min Range: -4.1103
Max Act: 4.1103. Min Act: -0.1700
Data Index: 1185342 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1103. Min Range: -4.1103
Max Act: 4.0478. Min Act: -0.1700
Data Index: 5550970 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1103. Min Range: -4.1103
Max Act: 4.0166. Min Act: -0.1700
Data Index: 6703897 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1103. Min Range: -4.1103
Max Act: 4.0166. Min Act: -0.1700
Data Index: 2641777 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9853. Min Act: -0.1700
Data Index: 5802032 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9853. Min Act: -0.1700
Data Index: 210088 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9540. Min Act: -0.1700
Data Index: 249438 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9540. Min Act: -0.1700
Data Index: 1831760 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9228. Min Act: -0.1700
Data Index: 7850563 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9228. Min Act: -0.1700
Data Index: 8490153 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9228. Min Act: -0.1700
Data Index: 4844150 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8915. Min Act: -0.1700
Data Index: 3975507 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9072. Min Act: -0.1700
Data Index: 2825506 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8915. Min Act: -0.1700
Data Index: 5014081 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8915. Min Act: -0.1700
Data Index: 7333583 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.9072. Min Act: -0.1700
Data Index: 1808374 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8759. Min Act: -0.1700
Data Index: 8041278 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8915. Min Act: -0.1700
Data Index: 4964067 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8915. Min Act: -0.1700
Data Index: 2161382 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1103. Min Range: -4.1103
Max Act: 3.8759. Min Act: -0.1700
Data Index: 1009132 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19