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

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

Neuron 3854 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0001

Data Index: 675852 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1342875 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1345835 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0636. Min Act: -0.0001

Data Index: 432799 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0609. Min Act: -0.0001

Data Index: 388644 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0628. Min Act: -0.0001

Data Index: 594034 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1285908 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1282408 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0598. Min Act: -0.0001

Data Index: 43025 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0567. Min Act: -0.0001

Data Index: 316964 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1179526 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0517. Min Act: -0.0001

Data Index: 735710 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1185483 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0551. Min Act: -0.0001

Data Index: 460005 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0514. Min Act: -0.0001

Data Index: 100807 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0513. Min Act: -0.0001

Data Index: 265041 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0533. Min Act: -0.0001

Data Index: 474222 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0521. Min Act: -0.0001

Data Index: 369798 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0518. Min Act: -0.0001

Data Index: 176308 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0512. Min Act: -0.0001

Data Index: 862311 (C4 (Web Text))

Max Activating Token Index: 365