Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1061. Min Range: -5.1061
Max Act: 5.1061. Min Act: -0.1700
Data Index: 2458696 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1061. Min Range: -5.1061
Max Act: 5.1061. Min Act: -0.1700
Data Index: 6934079 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.9498. Min Act: -0.1700
Data Index: 5533644 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.8248. Min Act: -0.1700
Data Index: 6408044 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7936. Min Act: -0.1700
Data Index: 3457994 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7936. Min Act: -0.1700
Data Index: 2327346 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7936. Min Act: -0.1700
Data Index: 83604 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7311. Min Act: -0.1700
Data Index: 8467063 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7623. Min Act: -0.1700
Data Index: 7593777 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7623. Min Act: -0.1700
Data Index: 635765 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7623. Min Act: -0.1700
Data Index: 4492580 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7623. Min Act: -0.1700
Data Index: 6249938 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7311. Min Act: -0.1700
Data Index: 3672935 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.6998. Min Act: -0.1700
Data Index: 6833895 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.7311. Min Act: -0.1700
Data Index: 1036650 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.6998. Min Act: -0.1700
Data Index: 7433795 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.6686. Min Act: -0.1700
Data Index: 6434067 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.6686. Min Act: -0.1700
Data Index: 1049830 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.6686. Min Act: -0.1700
Data Index: 230692 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1061. Min Range: -5.1061
Max Act: 4.6686. Min Act: -0.1700
Data Index: 2838607 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19