Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2782 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.3852. Min Act: -0.1700
Data Index: 1173571 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.1977. Min Act: -0.1700
Data Index: 377177 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0414. Min Act: -0.1700
Data Index: 4802677 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0414. Min Act: -0.1700
Data Index: 1901093 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3852. Min Range: -5.3852
Max Act: 5.0102. Min Act: -0.1700
Data Index: 3254705 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9477. Min Act: -0.1700
Data Index: 305166 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.9477. Min Act: -0.1700
Data Index: 245369 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.8852. Min Act: -0.1700
Data Index: 859750 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.8852. Min Act: -0.1700
Data Index: 113877 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.8539. Min Act: -0.1700
Data Index: 3854628 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.8539. Min Act: -0.1700
Data Index: 4177860 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5445611 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.8227. Min Act: -0.1700
Data Index: 1763175 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5851897 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7914. Min Act: -0.1700
Data Index: 6816790 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.8227. Min Act: -0.1700
Data Index: 7018413 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7914. Min Act: -0.1700
Data Index: 6001448 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7914. Min Act: -0.1700
Data Index: 2183033 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7602. Min Act: -0.1700
Data Index: 6986395 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3852. Min Range: -5.3852
Max Act: 4.7914. Min Act: -0.1700
Data Index: 5993555 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19