Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2957. Min Act: -0.1700
Data Index: 8277626 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2781. Min Act: -0.1700
Data Index: 3461343 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2428. Min Act: -0.1700
Data Index: 7711303 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2428. Min Act: -0.1700
Data Index: 5651885 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2428. Min Act: -0.1700
Data Index: 4282564 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2428. Min Act: -0.1700
Data Index: 6589054 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2252. Min Act: -0.1700
Data Index: 5186604 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 860060 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 5539577 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2252. Min Act: -0.1700
Data Index: 474836 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.1900. Min Act: -0.1700
Data Index: 3934858 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 1651366 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 5247673 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.1900. Min Act: -0.1700
Data Index: 602017 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 1176994 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 8275407 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.2076. Min Act: -0.1700
Data Index: 8140397 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.1900. Min Act: -0.1700
Data Index: 3005663 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.1900. Min Act: -0.1700
Data Index: 3093415 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2957. Min Range: -1.2957
Max Act: 1.1900. Min Act: -0.1700
Data Index: 3245343 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19