Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1777 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.8901. Min Act: -0.1700
Data Index: 8637842 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.8276. Min Act: -0.1700
Data Index: 8686325 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.7964. Min Act: -0.1700
Data Index: 2100299 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.7651. Min Act: -0.1700
Data Index: 66274 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.7339. Min Act: -0.1698
Data Index: 6114136 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.7026. Min Act: -0.1700
Data Index: 7307812 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.7026. Min Act: -0.1700
Data Index: 4412784 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6714. Min Act: -0.1700
Data Index: 562719 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.7026. Min Act: -0.1700
Data Index: 4991476 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6401. Min Act: -0.1700
Data Index: 608344 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6401. Min Act: -0.1700
Data Index: 6558860 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6401. Min Act: -0.1700
Data Index: 2486968 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6401. Min Act: -0.1700
Data Index: 4784452 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6401. Min Act: -0.1700
Data Index: 149501 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6401. Min Act: -0.1700
Data Index: 8344903 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6089. Min Act: -0.1700
Data Index: 974383 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6089. Min Act: -0.1700
Data Index: 5143151 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6089. Min Act: -0.1700
Data Index: 6712584 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.6089. Min Act: -0.1700
Data Index: 6766460 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8901. Min Range: -6.8901
Max Act: 6.5776. Min Act: -0.1700
Data Index: 2008902 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19