Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 155 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.5832. Min Act: -0.1700
Data Index: 2021168 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.5520. Min Act: -0.1700
Data Index: 6449913 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.5207. Min Act: -0.1700
Data Index: 5430137 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.5520. Min Act: -0.1700
Data Index: 5118561 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.4895. Min Act: -0.1700
Data Index: 1525414 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.4895. Min Act: -0.1700
Data Index: 1912003 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.4582. Min Act: -0.1700
Data Index: 94017 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.4270. Min Act: -0.1700
Data Index: 1649430 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.4270. Min Act: -0.1700
Data Index: 2270827 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.4270. Min Act: -0.1700
Data Index: 3648622 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3957. Min Act: -0.1700
Data Index: 6879809 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3957. Min Act: -0.1700
Data Index: 30617 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3645. Min Act: -0.1700
Data Index: 5055463 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3957. Min Act: -0.1700
Data Index: 8069532 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3645. Min Act: -0.1700
Data Index: 999566 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3020. Min Act: -0.1700
Data Index: 4531222 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3020. Min Act: -0.1700
Data Index: 2220699 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.2707. Min Act: -0.1700
Data Index: 4340613 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3020. Min Act: -0.1700
Data Index: 1539422 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5832. Min Range: -7.5832
Max Act: 7.3020. Min Act: -0.1700
Data Index: 2777462 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19