Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1634 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 4268769 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8985. Min Act: -0.1700
Data Index: 496501 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1265719 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1805341 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7735. Min Act: -0.1700
Data Index: 4509858 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 8518872 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 1796695 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 6890897 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6798. Min Act: -0.1700
Data Index: 8727306 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 5511458 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 953917 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7423. Min Act: -0.1700
Data Index: 1518088 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 3946766 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.7110. Min Act: -0.1700
Data Index: 1831631 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6798. Min Act: -0.1700
Data Index: 3967537 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6173. Min Act: -0.1700
Data Index: 7902986 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6798. Min Act: -0.1700
Data Index: 8427707 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6485. Min Act: -0.1700
Data Index: 7304432 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.6485. Min Act: -0.1700
Data Index: 2503811 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9923. Min Range: -5.9923
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4691737 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19