Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.7764. Min Act: -0.1700
Data Index: 5597093 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.7923. Min Act: -0.1700
Data Index: 7424380 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.7923. Min Act: -0.1700
Data Index: 1736822 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.7285. Min Act: -0.1700
Data Index: 3686470 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.7125. Min Act: -0.1700
Data Index: 2965661 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6805. Min Act: -0.1700
Data Index: 1692013 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6805. Min Act: -0.1700
Data Index: 5211214 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6645. Min Act: -0.1700
Data Index: 3626544 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6965. Min Act: -0.1700
Data Index: 7731076 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6805. Min Act: -0.1700
Data Index: 1651254 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6645. Min Act: -0.1700
Data Index: 6942936 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6805. Min Act: -0.1700
Data Index: 7318230 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6805. Min Act: -0.1700
Data Index: 4829390 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.7125. Min Act: -0.1700
Data Index: 6997486 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6645. Min Act: -0.1700
Data Index: 7218904 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6645. Min Act: -0.1700
Data Index: 3609114 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6645. Min Act: -0.1700
Data Index: 4427283 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6484. Min Act: -0.1700
Data Index: 6918817 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6645. Min Act: -0.1700
Data Index: 4433203 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7923. Min Range: -2.7923
Max Act: 2.6484. Min Act: -0.1700
Data Index: 7397394 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19