Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0430. Min Range: -6.0430
Max Act: 6.0430. Min Act: -0.1700
Data Index: 5644563 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.9180. Min Act: -0.1700
Data Index: 6188981 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.8868. Min Act: -0.1700
Data Index: 6719675 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.8555. Min Act: -0.1700
Data Index: 7960391 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.8243. Min Act: -0.1700
Data Index: 2932035 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.8243. Min Act: -0.1700
Data Index: 1918988 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.8243. Min Act: -0.1700
Data Index: 4801734 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7930. Min Act: -0.1700
Data Index: 2359838 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5658357 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7618. Min Act: -0.1700
Data Index: 6088184 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7618. Min Act: -0.1700
Data Index: 2607560 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7305. Min Act: -0.1700
Data Index: 1583672 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.6993. Min Act: -0.1700
Data Index: 4234921 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7305. Min Act: -0.1700
Data Index: 7194884 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7305. Min Act: -0.1700
Data Index: 4502995 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7305. Min Act: -0.1700
Data Index: 3407816 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.7305. Min Act: -0.1700
Data Index: 5330675 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.6993. Min Act: -0.1700
Data Index: 446138 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.6993. Min Act: -0.1700
Data Index: 1119648 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0430. Min Range: -6.0430
Max Act: 5.6993. Min Act: -0.1700
Data Index: 4609890 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19