Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.8304. Min Act: -0.1700
Data Index: 7456676 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.6741. Min Act: -0.1700
Data Index: 3263064 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.6429. Min Act: -0.1700
Data Index: 5600448 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.5804. Min Act: -0.1700
Data Index: 4973376 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.4554. Min Act: -0.1700
Data Index: 1046852 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.3929. Min Act: -0.1700
Data Index: 4460751 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.2366. Min Act: -0.1700
Data Index: 6557559 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.2366. Min Act: -0.1700
Data Index: 8279512 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.2366. Min Act: -0.1700
Data Index: 6891098 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1741. Min Act: -0.1700
Data Index: 3905933 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1429. Min Act: -0.1700
Data Index: 712794 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1741. Min Act: -0.1700
Data Index: 3977769 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1116. Min Act: -0.1700
Data Index: 7062065 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1116. Min Act: -0.1700
Data Index: 1769828 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1116. Min Act: -0.1700
Data Index: 7375090 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2585193 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.0804. Min Act: -0.1700
Data Index: 4862189 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.1116. Min Act: -0.1700
Data Index: 6820623 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.0804. Min Act: -0.1700
Data Index: 2612828 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8304. Min Range: -6.8304
Max Act: 6.0491. Min Act: -0.1700
Data Index: 494155 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19