Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.9617. Min Act: -0.1700
Data Index: 71580 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.8992. Min Act: -0.1700
Data Index: 6227573 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 7953666 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7742. Min Act: -0.1700
Data Index: 4883984 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 4064247 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 6857170 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7117. Min Act: -0.1700
Data Index: 6983831 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 3817467 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.7430. Min Act: -0.1700
Data Index: 6561438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6805. Min Act: -0.1700
Data Index: 6921864 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6492. Min Act: -0.1700
Data Index: 8525037 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6805. Min Act: -0.1700
Data Index: 8407753 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6492. Min Act: -0.1700
Data Index: 4065137 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6492. Min Act: -0.1700
Data Index: 2742002 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6492. Min Act: -0.1700
Data Index: 1182699 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.5867. Min Act: -0.1700
Data Index: 1179642 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6180. Min Act: -0.1700
Data Index: 7970445 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6180. Min Act: -0.1700
Data Index: 5196858 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.6180. Min Act: -0.1700
Data Index: 1928637 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9617. Min Range: -4.9617
Max Act: 4.5867. Min Act: -0.1700
Data Index: 557885 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19