Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.8891. Min Act: -0.1700
Data Index: 451200 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.3579. Min Act: -0.1700
Data Index: 6671007 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.3579. Min Act: -0.1700
Data Index: 2247674 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.3266. Min Act: -0.1700
Data Index: 1561872 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2641. Min Act: -0.1700
Data Index: 1616645 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2954. Min Act: -0.1700
Data Index: 1177941 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2641. Min Act: -0.1700
Data Index: 803508 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.1704. Min Act: -0.1700
Data Index: 5460564 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2016. Min Act: -0.1700
Data Index: 1058066 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2016. Min Act: -0.1700
Data Index: 1132630 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.1079. Min Act: -0.1700
Data Index: 6763484 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.1079. Min Act: -0.1700
Data Index: 6397245 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0766. Min Act: -0.1700
Data Index: 2236253 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0454. Min Act: -0.1700
Data Index: 4399512 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0766. Min Act: -0.1700
Data Index: 5341865 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0766. Min Act: -0.1700
Data Index: 7958908 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0141. Min Act: -0.1700
Data Index: 7574121 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0454. Min Act: -0.1700
Data Index: 8706386 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0141. Min Act: -0.1700
Data Index: 6979987 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.0141. Min Act: -0.1700
Data Index: 1550207 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19