Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5075 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.4869. Min Act: -0.0000

Data Index: 1073778 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.4359. Min Act: -0.0000

Data Index: 13822 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.3550. Min Act: -0.0000

Data Index: 530720 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.3779. Min Act: -0.0000

Data Index: 375072 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.4441. Min Act: -0.0000

Data Index: 78657 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2060. Min Act: -0.0000

Data Index: 771493 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2810. Min Act: -0.0000

Data Index: 340965 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.5058. Min Act: -0.0000

Data Index: 315764 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.0857. Min Act: -0.0001

Data Index: 775835 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1094432 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2841. Min Act: -0.0000

Data Index: 569179 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2697. Min Act: -0.0001

Data Index: 561221 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2939. Min Act: -0.0000

Data Index: 431969 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.3098. Min Act: -0.0001

Data Index: 1016859 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.1600. Min Act: -0.0000

Data Index: 678683 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.2272. Min Act: -0.0000

Data Index: 915670 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.1546. Min Act: -0.0000

Data Index: 477065 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.1372. Min Act: -0.0000

Data Index: 567179 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.0758. Min Act: -0.0000

Data Index: 441504 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.5058. Min Range: -1.5058

Max Act: 1.0798. Min Act: -0.0000

Data Index: 111419 (C4 (Web Text))

Max Activating Token Index: 715