Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2123 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0548. Min Range: -7.0548
Max Act: 7.0548. Min Act: -0.1700
Data Index: 4012783 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.7423. Min Act: -0.1700
Data Index: 232659 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.6798. Min Act: -0.1700
Data Index: 1935392 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.6173. Min Act: -0.1700
Data Index: 5561860 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.5548. Min Act: -0.1700
Data Index: 7345021 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.5236. Min Act: -0.1700
Data Index: 2412669 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.4923. Min Act: -0.1700
Data Index: 5245459 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.4611. Min Act: -0.1700
Data Index: 8495377 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.4298. Min Act: -0.1700
Data Index: 1756134 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.4298. Min Act: -0.1700
Data Index: 7667348 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.4298. Min Act: -0.1700
Data Index: 5326894 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3986. Min Act: -0.1700
Data Index: 2710036 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3673. Min Act: -0.1700
Data Index: 2974005 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3673. Min Act: -0.1700
Data Index: 4646890 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3673. Min Act: -0.1700
Data Index: 1756573 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3673. Min Act: -0.1700
Data Index: 1668481 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3361. Min Act: -0.1700
Data Index: 766655 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3361. Min Act: -0.1700
Data Index: 2054726 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3361. Min Act: -0.1700
Data Index: 7030782 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0548. Min Range: -7.0548
Max Act: 6.3361. Min Act: -0.1700
Data Index: 5201728 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19