Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.6579. Min Act: -0.1700
Data Index: 3186683 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.6579. Min Act: -0.1700
Data Index: 7612503 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.6267. Min Act: -0.1700
Data Index: 720327 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.6267. Min Act: -0.1700
Data Index: 7195410 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.5329. Min Act: -0.1700
Data Index: 1046320 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.4704. Min Act: -0.1700
Data Index: 117073 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.4704. Min Act: -0.1700
Data Index: 6358187 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.4079. Min Act: -0.1700
Data Index: 7556965 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3767. Min Act: -0.1700
Data Index: 6086652 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3767. Min Act: -0.1700
Data Index: 5281734 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3454. Min Act: -0.1700
Data Index: 5563722 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 7153379 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 1721935 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 7236510 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 8423467 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 6155141 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.2829. Min Act: -0.1700
Data Index: 5383798 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.3142. Min Act: -0.1700
Data Index: 4191263 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.2517. Min Act: -0.1700
Data Index: 553831 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6579. Min Range: -6.6579
Max Act: 6.2517. Min Act: -0.1700
Data Index: 1573726 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19