Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.7405. Min Act: -0.1700
Data Index: 3105790 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.6780. Min Act: -0.1700
Data Index: 344702 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.3030. Min Act: -0.1700
Data Index: 6830838 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.3343. Min Act: -0.1700
Data Index: 8088979 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.2718. Min Act: -0.1700
Data Index: 7116805 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.1155. Min Act: -0.1700
Data Index: 1944830 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.0843. Min Act: -0.1700
Data Index: 8693575 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.1155. Min Act: -0.1700
Data Index: 8703859 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.0530. Min Act: -0.1700
Data Index: 1950405 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.0530. Min Act: -0.1700
Data Index: 8621335 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9905. Min Act: -0.1700
Data Index: 4721209 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9905. Min Act: -0.1700
Data Index: 3613629 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9905. Min Act: -0.1700
Data Index: 7928914 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7405. Min Range: -6.7405
Max Act: 6.0218. Min Act: -0.1700
Data Index: 3916172 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9593. Min Act: -0.1700
Data Index: 3780286 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9593. Min Act: -0.1700
Data Index: 6603576 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9593. Min Act: -0.1700
Data Index: 7747963 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9280. Min Act: -0.1700
Data Index: 8410166 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9280. Min Act: -0.1700
Data Index: 8438398 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7405. Min Range: -6.7405
Max Act: 5.9280. Min Act: -0.1700
Data Index: 5783552 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19