Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.6407. Min Act: -0.1700
Data Index: 4337298 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.2657. Min Act: -0.1700
Data Index: 2786641 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.2032. Min Act: -0.1700
Data Index: 280293 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.2032. Min Act: -0.1700
Data Index: 3197958 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.0782. Min Act: -0.1700
Data Index: 1416418 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.0157. Min Act: -0.1700
Data Index: 5272617 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.0157. Min Act: -0.1700
Data Index: 2202971 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.9532. Min Act: -0.1700
Data Index: 4249426 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.9532. Min Act: -0.1700
Data Index: 3102929 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.6407. Min Range: -15.6407
Max Act: 15.0157. Min Act: -0.1700
Data Index: 6242053 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.8907. Min Act: -0.1700
Data Index: 7173364 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.9532. Min Act: -0.1700
Data Index: 7409500 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.8907. Min Act: -0.1700
Data Index: 3604145 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.8907. Min Act: -0.1700
Data Index: 533015 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.8282. Min Act: -0.1700
Data Index: 5148230 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.8282. Min Act: -0.1700
Data Index: 8447725 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.8282. Min Act: -0.1700
Data Index: 340806 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.7032. Min Act: -0.1700
Data Index: 800120 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.7657. Min Act: -0.1700
Data Index: 5054594 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.6407. Min Range: -15.6407
Max Act: 14.7657. Min Act: -0.1700
Data Index: 5849570 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19