Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.2251. Min Act: -0.1700
Data Index: 950892 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.2251. Min Act: -0.1700
Data Index: 3986772 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.1001. Min Act: -0.1700
Data Index: 2435975 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.0376. Min Act: -0.1700
Data Index: 5706397 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.0376. Min Act: -0.1700
Data Index: 514521 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.0376. Min Act: -0.1700
Data Index: 3986770 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.0063. Min Act: -0.1700
Data Index: 6688619 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2251. Min Range: -8.2251
Max Act: 8.0063. Min Act: -0.1700
Data Index: 8320754 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9751. Min Act: -0.1700
Data Index: 6050739 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9438. Min Act: -0.1700
Data Index: 6493759 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9438. Min Act: -0.1700
Data Index: 1694730 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9438. Min Act: -0.1700
Data Index: 4340497 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9751. Min Act: -0.1700
Data Index: 1280690 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9126. Min Act: -0.1700
Data Index: 1298368 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9126. Min Act: -0.1700
Data Index: 7603960 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9126. Min Act: -0.1700
Data Index: 3954406 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.9126. Min Act: -0.1700
Data Index: 8433224 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.8813. Min Act: -0.1700
Data Index: 2663161 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.8813. Min Act: -0.1700
Data Index: 5810468 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2251. Min Range: -8.2251
Max Act: 7.8501. Min Act: -0.1700
Data Index: 4348756 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19