Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2227 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.8909. Min Act: -0.1700
Data Index: 4379039 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.6409. Min Act: -0.1700
Data Index: 3808713 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.5784. Min Act: -0.1700
Data Index: 6557511 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.4534. Min Act: -0.1700
Data Index: 7150406 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.3909. Min Act: -0.1700
Data Index: 6524380 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.2971. Min Act: -0.1700
Data Index: 8809925 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.3284. Min Act: -0.1700
Data Index: 6302917 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.2659. Min Act: -0.1700
Data Index: 1144922 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.2034. Min Act: -0.1700
Data Index: 2929828 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.2034. Min Act: -0.1700
Data Index: 4820972 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.2346. Min Act: -0.1700
Data Index: 6349539 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1721. Min Act: -0.1700
Data Index: 518009 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1721. Min Act: -0.1700
Data Index: 4925197 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1409. Min Act: -0.1700
Data Index: 5907182 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1409. Min Act: -0.1700
Data Index: 8384587 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1409. Min Act: -0.1700
Data Index: 3185147 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1096. Min Act: -0.1700
Data Index: 4526706 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1096. Min Act: -0.1700
Data Index: 3230833 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7315797 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8909. Min Range: -6.8909
Max Act: 6.1409. Min Act: -0.1700
Data Index: 8379979 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19