Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2763 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.3687. Min Act: -0.1700
Data Index: 5461396 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.3062. Min Act: -0.1700
Data Index: 3189490 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.3062. Min Act: -0.1700
Data Index: 175209 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.2749. Min Act: -0.1700
Data Index: 7408511 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.2437. Min Act: -0.1700
Data Index: 6959063 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1812. Min Act: -0.1700
Data Index: 7323690 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1812. Min Act: -0.1700
Data Index: 3982711 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.1499. Min Act: -0.1700
Data Index: 1010715 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0874. Min Act: -0.1700
Data Index: 7108761 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0874. Min Act: -0.1700
Data Index: 8489789 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0249. Min Act: -0.1700
Data Index: 3039385 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0562. Min Act: -0.1700
Data Index: 1712331 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0249. Min Act: -0.1700
Data Index: 7736391 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0249. Min Act: -0.1700
Data Index: 2259091 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0249. Min Act: -0.1700
Data Index: 5536748 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0249. Min Act: -0.1700
Data Index: 3069479 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3687. Min Range: -6.3687
Max Act: 6.0249. Min Act: -0.1700
Data Index: 1398737 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9937. Min Act: -0.1700
Data Index: 3768984 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9937. Min Act: -0.1700
Data Index: 1160867 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3687. Min Range: -6.3687
Max Act: 5.9937. Min Act: -0.1700
Data Index: 1717450 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19