Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3697 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.7045. Min Act: -0.1700
Data Index: 3270654 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.4545. Min Act: -0.1700
Data Index: 2428791 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3920. Min Act: -0.1700
Data Index: 5683963 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3295. Min Act: -0.1700
Data Index: 281883 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3920. Min Act: -0.1700
Data Index: 1827247 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3295. Min Act: -0.1700
Data Index: 4898049 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3295. Min Act: -0.1700
Data Index: 3540816 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3295. Min Act: -0.1700
Data Index: 575740 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 2189119 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 4066749 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 8718741 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.3295. Min Act: -0.1700
Data Index: 8578487 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 7914184 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 7864156 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 1368533 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 7363203 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 626688 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2045. Min Act: -0.1700
Data Index: 2560587 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2670. Min Act: -0.1700
Data Index: 4321156 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7045. Min Range: -8.7045
Max Act: 8.2045. Min Act: -0.1700
Data Index: 1447327 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19