Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 366 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.5910. Min Act: -0.1700
Data Index: 8034252 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.2160. Min Act: -0.1700
Data Index: 2154163 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 4624709 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.1222. Min Act: -0.1700
Data Index: 4445882 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 5568526 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 4091901 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0285. Min Act: -0.1700
Data Index: 5350246 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0285. Min Act: -0.1700
Data Index: 5708784 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5910. Min Range: -6.5910
Max Act: 6.0285. Min Act: -0.1700
Data Index: 4355346 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9972. Min Act: -0.1700
Data Index: 4870346 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9972. Min Act: -0.1700
Data Index: 931807 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9660. Min Act: -0.1700
Data Index: 656964 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9660. Min Act: -0.1700
Data Index: 8332811 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9660. Min Act: -0.1700
Data Index: 4560553 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9660. Min Act: -0.1700
Data Index: 60680 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9347. Min Act: -0.1700
Data Index: 6247136 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9660. Min Act: -0.1700
Data Index: 729314 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9035. Min Act: -0.1700
Data Index: 234558 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9035. Min Act: -0.1700
Data Index: 6744072 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5910. Min Range: -6.5910
Max Act: 5.9035. Min Act: -0.1700
Data Index: 5355564 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19