Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1736 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1977. Min Act: -0.0001

Data Index: 642773 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1707. Min Act: -0.0001

Data Index: 461879 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1793. Min Act: -0.0002

Data Index: 636145 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1723. Min Act: -0.0001

Data Index: 232232 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1719. Min Act: -0.0002

Data Index: 1162656 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1625. Min Act: -0.0001

Data Index: 381729 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1816. Min Act: -0.0001

Data Index: 426810 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1784. Min Act: -0.0002

Data Index: 707151 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1915. Min Act: -0.0002

Data Index: 912742 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1762. Min Act: -0.0002

Data Index: 346722 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1769. Min Act: -0.0002

Data Index: 98031 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1684. Min Act: -0.0002

Data Index: 445930 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1673. Min Act: -0.0002

Data Index: 3407 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1797. Min Act: -0.0002

Data Index: 813863 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1872. Min Act: -0.0002

Data Index: 655526 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1611. Min Act: -0.0001

Data Index: 635394 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1766. Min Act: -0.0002

Data Index: 732692 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1651. Min Act: -0.0002

Data Index: 868434 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1659. Min Act: -0.0001

Data Index: 996729 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1693. Min Act: -0.0002

Data Index: 836123 (C4 (Web Text))

Max Activating Token Index: 104