Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5600 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.2895. Min Act: -0.1700
Data Index: 1319898 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.2270. Min Act: -0.1700
Data Index: 4790624 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.2270. Min Act: -0.1700
Data Index: 5741723 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.1645. Min Act: -0.1700
Data Index: 7678023 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.1645. Min Act: -0.1700
Data Index: 7115194 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.1645. Min Act: -0.1700
Data Index: 4877015 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.1645. Min Act: -0.1700
Data Index: 275930 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.1645. Min Act: -0.1700
Data Index: 8692336 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2895. Min Range: -10.2895
Max Act: 10.0395. Min Act: -0.1700
Data Index: 656070 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.9770. Min Act: -0.1700
Data Index: 1628218 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.9770. Min Act: -0.1700
Data Index: 2320658 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.9145. Min Act: -0.1700
Data Index: 7419975 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.9145. Min Act: -0.1700
Data Index: 7177811 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.9770. Min Act: -0.1700
Data Index: 4352707 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.8520. Min Act: -0.1700
Data Index: 1668155 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.8520. Min Act: -0.1700
Data Index: 1264044 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.8520. Min Act: -0.1700
Data Index: 5075756 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.9145. Min Act: -0.1700
Data Index: 4790623 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.8520. Min Act: -0.1700
Data Index: 3344613 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2895. Min Range: -10.2895
Max Act: 9.7895. Min Act: -0.1700
Data Index: 2815796 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19