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

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

Neuron 3735 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9002. Min Act: -0.0000

Data Index: 431645 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9996. Min Act: -0.0000

Data Index: 609434 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1105542 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9232. Min Act: -0.0000

Data Index: 325380 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5753. Min Act: -0.0000

Data Index: 1292543 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7505. Min Act: -0.0001

Data Index: 250816 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7516. Min Act: -0.0000

Data Index: 91208 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5567. Min Act: -0.0001

Data Index: 1279775 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6527. Min Act: -0.0000

Data Index: 923908 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5807. Min Act: -0.0000

Data Index: 529895 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4728. Min Act: -0.0000

Data Index: 1155739 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5792. Min Act: -0.0000

Data Index: 10795 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5496. Min Act: -0.0000

Data Index: 795492 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5022. Min Act: -0.0000

Data Index: 49784 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5145. Min Act: -0.0001

Data Index: 223864 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4836. Min Act: -0.0001

Data Index: 687132 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5195. Min Act: -0.0000

Data Index: 715878 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4879. Min Act: -0.0000

Data Index: 26493 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3544. Min Act: -0.0000

Data Index: 858962 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4535. Min Act: -0.0001

Data Index: 1155393 (C4 (Web Text))

Max Activating Token Index: 118