Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 957 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1075544 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1256516 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1161623 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1007788 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0554. Min Act: -0.0002

Data Index: 861558 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0576. Min Act: -0.0002

Data Index: 271302 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0575. Min Act: -0.0002

Data Index: 196694 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0564. Min Act: -0.0002

Data Index: 947904 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0530. Min Act: -0.0002

Data Index: 423215 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1189687 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0553. Min Act: -0.0002

Data Index: 435214 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0545. Min Act: -0.0002

Data Index: 94194 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1319814 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1059465 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1333949 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0556. Min Act: -0.0002

Data Index: 578175 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0542. Min Act: -0.0002

Data Index: 402852 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0511. Min Act: -0.0002

Data Index: 628514 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0503. Min Act: -0.0002

Data Index: 323738 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0548. Min Act: -0.0002

Data Index: 794443 (C4 (Web Text))

Max Activating Token Index: 707