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

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

Neuron 1012 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0003

Data Index: 153429 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0681. Min Act: -0.0003

Data Index: 467878 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0661. Min Act: -0.0003

Data Index: 602492 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0627. Min Act: -0.0003

Data Index: 573345 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0580. Min Act: -0.0003

Data Index: 617033 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0575. Min Act: -0.0003

Data Index: 157050 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0554. Min Act: -0.0002

Data Index: 405012 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0568. Min Act: -0.0003

Data Index: 772430 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0550. Min Act: -0.0003

Data Index: 108388 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0566. Min Act: -0.0003

Data Index: 110538 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0574. Min Act: -0.0003

Data Index: 505448 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1207180 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0562. Min Act: -0.0003

Data Index: 817911 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0537. Min Act: -0.0002

Data Index: 230879 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1184611 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0563. Min Act: -0.0002

Data Index: 182502 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0533. Min Act: -0.0002

Data Index: 847036 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0537. Min Act: -0.0002

Data Index: 102305 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1292919 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1221249 (C4 (Web Text))

Max Activating Token Index: 619