Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 80 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.6363. Min Act: -0.1027
Data Index: 3001943 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.6363. Min Act: -0.1027
Data Index: 3218464 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 5667707 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 7912988 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 439826 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 882517 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 7514693 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 634452 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 7299017 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 470420 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 6704459 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 5680978 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 2077500 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 3937874 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 1264975 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 3347123 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 3313375 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 2939889 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 2622251 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6363. Min Range: -1.6363
Max Act: 1.4084. Min Act: -0.1027
Data Index: 2399686 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19