Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1981 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.5537. Min Act: -0.1700
Data Index: 4967477 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.4912. Min Act: -0.1700
Data Index: 8201178 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.3037. Min Act: -0.1700
Data Index: 4670919 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.3037. Min Act: -0.1700
Data Index: 4667550 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.3037. Min Act: -0.1700
Data Index: 3355825 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.2412. Min Act: -0.1700
Data Index: 3503717 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.2099. Min Act: -0.1700
Data Index: 3170160 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.2099. Min Act: -0.1700
Data Index: 5226125 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.2099. Min Act: -0.1700
Data Index: 8201177 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1787. Min Act: -0.1700
Data Index: 4681052 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1787. Min Act: -0.1700
Data Index: 4967472 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1787. Min Act: -0.1700
Data Index: 110667 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1474. Min Act: -0.1700
Data Index: 5758224 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1474. Min Act: -0.1700
Data Index: 4967473 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 5448635 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1162. Min Act: -0.1700
Data Index: 3174334 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1162. Min Act: -0.1700
Data Index: 1337044 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.1162. Min Act: -0.1700
Data Index: 2466431 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 4967478 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5537. Min Range: -5.5537
Max Act: 5.0849. Min Act: -0.1700
Data Index: 5205084 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19