Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.2685. Min Act: -0.1700
Data Index: 8578187 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.2213. Min Act: -0.1700
Data Index: 2046748 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.2056. Min Act: -0.1700
Data Index: 3199689 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1742. Min Act: -0.1700
Data Index: 1394185 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1742. Min Act: -0.1700
Data Index: 2575638 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1742. Min Act: -0.1700
Data Index: 7866250 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1584. Min Act: -0.1700
Data Index: 1739268 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1742. Min Act: -0.1700
Data Index: 284578 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1584. Min Act: -0.1700
Data Index: 3645663 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1269. Min Act: -0.1700
Data Index: 7139249 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1269. Min Act: -0.1700
Data Index: 3347837 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1427. Min Act: -0.1700
Data Index: 814167 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1112. Min Act: -0.1700
Data Index: 2311145 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1427. Min Act: -0.1700
Data Index: 950957 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1269. Min Act: -0.1700
Data Index: 7362055 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1269. Min Act: -0.1700
Data Index: 8661371 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1112. Min Act: -0.1700
Data Index: 8266421 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1112. Min Act: -0.1700
Data Index: 4922166 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.1112. Min Act: -0.1700
Data Index: 2852569 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2685. Min Range: -3.2685
Max Act: 3.0954. Min Act: -0.1700
Data Index: 2032316 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19