Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4653 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0002

Data Index: 460044 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0659. Min Act: -0.0002

Data Index: 981518 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0667. Min Act: -0.0002

Data Index: 752568 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0645. Min Act: -0.0002

Data Index: 661127 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0632. Min Act: -0.0002

Data Index: 636903 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1298006 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0622. Min Act: -0.0002

Data Index: 360303 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1348354 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0609. Min Act: -0.0002

Data Index: 656842 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1286553 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0629. Min Act: -0.0002

Data Index: 263138 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0599. Min Act: -0.0002

Data Index: 170301 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1056047 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0598. Min Act: -0.0002

Data Index: 799258 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0602. Min Act: -0.0002

Data Index: 313520 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0583. Min Act: -0.0002

Data Index: 68361 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0578. Min Act: -0.0002

Data Index: 27324 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0577. Min Act: -0.0002

Data Index: 289781 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1054519 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0569. Min Act: -0.0002

Data Index: 57161 (C4 (Web Text))

Max Activating Token Index: 169