Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.1326. Min Act: -0.1700
Data Index: 2544621 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.1013. Min Act: -0.1700
Data Index: 4483780 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.1013. Min Act: -0.1700
Data Index: 7869769 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.0701. Min Act: -0.1700
Data Index: 1655695 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.0076. Min Act: -0.1700
Data Index: 2144381 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.0076. Min Act: -0.1700
Data Index: 798150 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1326. Min Range: -5.1326
Max Act: 5.0076. Min Act: -0.1700
Data Index: 2725333 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9451. Min Act: -0.1700
Data Index: 578581 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9451. Min Act: -0.1700
Data Index: 800830 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9763. Min Act: -0.1700
Data Index: 2513318 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 1762452 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 285509 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 7003734 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9451. Min Act: -0.1700
Data Index: 1732639 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 6604318 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 3480085 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 6090688 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9451. Min Act: -0.1700
Data Index: 96569 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 5692516 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1326. Min Range: -5.1326
Max Act: 4.9138. Min Act: -0.1700
Data Index: 1141152 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19