Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6359 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5833. Min Range: -5.5833
Max Act: 5.5833. Min Act: -0.1700
Data Index: 5652105 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5833. Min Range: -5.5833
Max Act: 5.1770. Min Act: -0.1700
Data Index: 8605734 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5833. Min Range: -5.5833
Max Act: 5.1145. Min Act: -0.1700
Data Index: 4963351 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5833. Min Range: -5.5833
Max Act: 5.0208. Min Act: -0.1700
Data Index: 462156 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5833. Min Range: -5.5833
Max Act: 5.0208. Min Act: -0.1700
Data Index: 3510626 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5833. Min Range: -5.5833
Max Act: 5.0208. Min Act: -0.1700
Data Index: 3058462 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.9895. Min Act: -0.1700
Data Index: 12865 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.9583. Min Act: -0.1700
Data Index: 963704 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.9270. Min Act: -0.1700
Data Index: 3283120 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.9270. Min Act: -0.1700
Data Index: 1713665 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.9270. Min Act: -0.1700
Data Index: 2318276 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5517966 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8958. Min Act: -0.1700
Data Index: 681851 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8958. Min Act: -0.1700
Data Index: 7047886 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8645. Min Act: -0.1700
Data Index: 3511906 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8645. Min Act: -0.1700
Data Index: 4027284 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8645. Min Act: -0.1700
Data Index: 2963049 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8645. Min Act: -0.1700
Data Index: 4366346 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8333. Min Act: -0.1700
Data Index: 6870114 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5833. Min Range: -5.5833
Max Act: 4.8333. Min Act: -0.1700
Data Index: 4357470 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19