Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.4829. Min Act: -0.1700
Data Index: 3103764 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.3267. Min Act: -0.1700
Data Index: 5544748 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.2642. Min Act: -0.1700
Data Index: 8765388 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.2017. Min Act: -0.1700
Data Index: 4025312 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.1392. Min Act: -0.1700
Data Index: 7641377 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.1079. Min Act: -0.1700
Data Index: 5894252 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0454. Min Act: -0.1700
Data Index: 1886948 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0767. Min Act: -0.1700
Data Index: 4667799 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0454. Min Act: -0.1700
Data Index: 4467999 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0142. Min Act: -0.1700
Data Index: 2816162 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0142. Min Act: -0.1700
Data Index: 110111 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0142. Min Act: -0.1700
Data Index: 6405546 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0142. Min Act: -0.1700
Data Index: 508753 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4829. Min Range: -6.4829
Max Act: 5.9829. Min Act: -0.1700
Data Index: 4582141 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4829. Min Range: -6.4829
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3208579 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4829. Min Range: -6.4829
Max Act: 5.9829. Min Act: -0.1700
Data Index: 6693424 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4829. Min Range: -6.4829
Max Act: 5.9829. Min Act: -0.1700
Data Index: 6067855 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4829. Min Range: -6.4829
Max Act: 6.0142. Min Act: -0.1700
Data Index: 4016095 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4829. Min Range: -6.4829
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3623180 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4829. Min Range: -6.4829
Max Act: 5.9517. Min Act: -0.1700
Data Index: 2137725 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19