Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2094 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.9063. Min Act: -0.1700
Data Index: 2638997 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.8036. Min Act: -0.1700
Data Index: 2575986 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7691. Min Act: -0.1697
Data Index: 5132682 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7346. Min Act: -0.1700
Data Index: 6603025 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7432. Min Act: -0.1700
Data Index: 2188652 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7432. Min Act: -0.1698
Data Index: 140330 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7432. Min Act: -0.1700
Data Index: 7101725 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7346. Min Act: -0.1700
Data Index: 5203773 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7432. Min Act: -0.1700
Data Index: 6714503 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7173. Min Act: -0.1700
Data Index: 8278393 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7259. Min Act: -0.1700
Data Index: 4990885 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7259. Min Act: -0.1700
Data Index: 4877916 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7173. Min Act: -0.1700
Data Index: 4520265 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7259. Min Act: -0.1700
Data Index: 1747099 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7173. Min Act: -0.1700
Data Index: 2006684 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7173. Min Act: -0.1700
Data Index: 241405 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7173. Min Act: -0.1700
Data Index: 7271693 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7086. Min Act: -0.1700
Data Index: 2243899 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7259. Min Act: -0.1700
Data Index: 7779871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9063. Min Range: -1.9063
Max Act: 1.7086. Min Act: -0.1700
Data Index: 4533909 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19