Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4918 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5472873 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.6625. Min Act: -0.1700
Data Index: 7126710 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.6313. Min Act: -0.1700
Data Index: 1079593 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.6000. Min Act: -0.1700
Data Index: 6543321 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.5375. Min Act: -0.1700
Data Index: 1261674 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.5375. Min Act: -0.1700
Data Index: 2799221 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.5375. Min Act: -0.1700
Data Index: 4847658 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.5063. Min Act: -0.1700
Data Index: 1660855 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4750. Min Act: -0.1700
Data Index: 6229875 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4750. Min Act: -0.1700
Data Index: 2382609 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4750. Min Act: -0.1700
Data Index: 1059326 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4125. Min Act: -0.1700
Data Index: 458646 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4750. Min Act: -0.1700
Data Index: 6912504 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4438. Min Act: -0.1700
Data Index: 8421055 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4438. Min Act: -0.1700
Data Index: 7929485 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4438. Min Act: -0.1700
Data Index: 6016377 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4438. Min Act: -0.1700
Data Index: 3334790 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4125. Min Act: -0.1700
Data Index: 7771979 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4125. Min Act: -0.1700
Data Index: 3137409 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6625. Min Range: -4.6625
Max Act: 4.4125. Min Act: -0.1700
Data Index: 1660854 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19