Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2406 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.1751. Min Act: -0.1700
Data Index: 3907636 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.2376. Min Act: -0.1700
Data Index: 4963764 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.1751. Min Act: -0.1700
Data Index: 2522501 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.0813. Min Act: -0.1700
Data Index: 1414930 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.0501. Min Act: -0.1700
Data Index: 7989227 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.0501. Min Act: -0.1700
Data Index: 4617749 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2376. Min Range: -8.2376
Max Act: 8.0501. Min Act: -0.1700
Data Index: 7933437 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.9876. Min Act: -0.1700
Data Index: 6198871 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.9563. Min Act: -0.1700
Data Index: 4256659 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.9563. Min Act: -0.1700
Data Index: 722771 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.9251. Min Act: -0.1700
Data Index: 4087819 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.9251. Min Act: -0.1700
Data Index: 4726964 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.8938. Min Act: -0.1700
Data Index: 941715 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.8313. Min Act: -0.1700
Data Index: 6449065 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.7688. Min Act: -0.1699
Data Index: 5110971 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.7688. Min Act: -0.1700
Data Index: 6977150 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.7063. Min Act: -0.1700
Data Index: 1392768 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.6438. Min Act: -0.1700
Data Index: 6433307 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.6438. Min Act: -0.1700
Data Index: 7754484 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2376. Min Range: -8.2376
Max Act: 7.6751. Min Act: -0.1700
Data Index: 776260 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19