Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2662. Min Range: -12.2662
Max Act: 12.2662. Min Act: -0.1700
Data Index: 3093314 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2662. Min Range: -12.2662
Max Act: 12.2037. Min Act: -0.1700
Data Index: 4471537 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2662. Min Range: -12.2662
Max Act: 12.1412. Min Act: -0.1699
Data Index: 6015211 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2662. Min Range: -12.2662
Max Act: 12.0787. Min Act: -0.1700
Data Index: 6344899 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.9537. Min Act: -0.1700
Data Index: 2447889 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.8912. Min Act: -0.1700
Data Index: 5563529 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.8912. Min Act: -0.1700
Data Index: 5654266 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.8287. Min Act: -0.1700
Data Index: 7509939 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.8287. Min Act: -0.1700
Data Index: 5583202 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.8287. Min Act: -0.1700
Data Index: 1011552 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.7662. Min Act: -0.1700
Data Index: 7960924 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.7037. Min Act: -0.1700
Data Index: 301253 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.7037. Min Act: -0.1700
Data Index: 481632 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.7037. Min Act: -0.1700
Data Index: 7204633 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.6412. Min Act: -0.1700
Data Index: 513873 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.5162. Min Act: -0.1700
Data Index: 7554585 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.5162. Min Act: -0.1700
Data Index: 1944788 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.5162. Min Act: -0.1700
Data Index: 487317 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.5162. Min Act: -0.1700
Data Index: 6932593 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2662. Min Range: -12.2662
Max Act: 11.5162. Min Act: -0.1700
Data Index: 4508112 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19