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

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

Neuron 4270 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: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0002

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1620. Min Act: -0.0002

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1335. Min Act: -0.0002

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0882. Min Act: -0.0002

Data Index: 1015769 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1082564 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1161106 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0744. Min Act: -0.0002

Data Index: 310534 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0676. Min Act: -0.0002

Data Index: 584198 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0700. Min Act: -0.0003

Data Index: 59942 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0605. Min Act: -0.0002

Data Index: 13487 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0629. Min Act: -0.0002

Data Index: 449120 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1261303 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0616. Min Act: -0.0003

Data Index: 721137 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1147405 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0614. Min Act: -0.0002

Data Index: 162499 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0659. Min Act: -0.0002

Data Index: 680430 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0602. Min Act: -0.0002

Data Index: 480378 (C4 (Web Text))

Max Activating Token Index: 48