Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1514 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1348. Min Range: -8.1348
Max Act: 8.1348. Min Act: -0.1700
Data Index: 3357892 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1348. Min Range: -8.1348
Max Act: 8.1348. Min Act: -0.1700
Data Index: 3789083 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1348. Min Range: -8.1348
Max Act: 8.0723. Min Act: -0.1700
Data Index: 2023364 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1348. Min Range: -8.1348
Max Act: 8.0723. Min Act: -0.1700
Data Index: 2154826 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1348. Min Range: -8.1348
Max Act: 8.0098. Min Act: -0.1700
Data Index: 6954797 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.9473. Min Act: -0.1700
Data Index: 7943019 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 6185009 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 8011459 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8223. Min Act: -0.1700
Data Index: 2101159 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8223. Min Act: -0.1700
Data Index: 5988004 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8848. Min Act: -0.1700
Data Index: 7417249 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8223. Min Act: -0.1700
Data Index: 4562998 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.6973. Min Act: -0.1700
Data Index: 5404783 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.7598. Min Act: -0.1700
Data Index: 6758906 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8223. Min Act: -0.1700
Data Index: 1586111 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.8223. Min Act: -0.1700
Data Index: 6288204 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.7598. Min Act: -0.1700
Data Index: 6225171 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.6973. Min Act: -0.1700
Data Index: 5567845 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.7598. Min Act: -0.1700
Data Index: 6980015 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1348. Min Range: -8.1348
Max Act: 7.7598. Min Act: -0.1700
Data Index: 3192065 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19