Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2010 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2431. Min Range: -12.2431
Max Act: 12.2431. Min Act: -0.1700
Data Index: 8430617 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2431. Min Range: -12.2431
Max Act: 12.1806. Min Act: -0.1700
Data Index: 3943777 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2431. Min Range: -12.2431
Max Act: 12.0556. Min Act: -0.1700
Data Index: 6467058 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.9931. Min Act: -0.1700
Data Index: 5554722 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.9931. Min Act: -0.1700
Data Index: 949526 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.9306. Min Act: -0.1700
Data Index: 8350742 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.9306. Min Act: -0.1700
Data Index: 848542 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.9306. Min Act: -0.1700
Data Index: 2153748 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.9306. Min Act: -0.1700
Data Index: 4113087 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.8681. Min Act: -0.1700
Data Index: 5036700 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.8681. Min Act: -0.1700
Data Index: 6716394 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.8681. Min Act: -0.1700
Data Index: 4186752 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.7431. Min Act: -0.1700
Data Index: 1532710 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.7431. Min Act: -0.1700
Data Index: 2416594 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.7431. Min Act: -0.1700
Data Index: 2968764 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.7431. Min Act: -0.1700
Data Index: 4676119 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.7431. Min Act: -0.1700
Data Index: 1095550 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.6806. Min Act: -0.1700
Data Index: 6953044 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.6181. Min Act: -0.1700
Data Index: 3296497 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2431. Min Range: -12.2431
Max Act: 11.6806. Min Act: -0.1700
Data Index: 5265221 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19