Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3190 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0115. Min Range: -2.0115
Max Act: 2.0115. Min Act: -0.1700
Data Index: 690480 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.9438. Min Act: -0.1700
Data Index: 7491769 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8756. Min Act: -0.1700
Data Index: 1033382 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8927. Min Act: -0.1700
Data Index: 8323422 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8927. Min Act: -0.1700
Data Index: 491696 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8414. Min Act: -0.1700
Data Index: 1140714 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8585. Min Act: -0.1700
Data Index: 2246260 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8242. Min Act: -0.1700
Data Index: 3645232 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8414. Min Act: -0.1700
Data Index: 478123 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8242. Min Act: -0.1700
Data Index: 8402140 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8414. Min Act: -0.1700
Data Index: 4114865 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8414. Min Act: -0.1700
Data Index: 1481834 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8242. Min Act: -0.1700
Data Index: 642236 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8071. Min Act: -0.1700
Data Index: 7198427 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8071. Min Act: -0.1700
Data Index: 4992667 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8071. Min Act: -0.1700
Data Index: 8512875 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.7899. Min Act: -0.1700
Data Index: 6634006 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8071. Min Act: -0.1700
Data Index: 7160778 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.8071. Min Act: -0.1700
Data Index: 3116116 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0115. Min Range: -2.0115
Max Act: 1.7899. Min Act: -0.1700
Data Index: 837652 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19