Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1958 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1304286 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1065158 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0625. Min Act: -0.0003

Data Index: 420832 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0604. Min Act: -0.0003

Data Index: 986845 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0587. Min Act: -0.0004

Data Index: 1212007 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0627. Min Act: -0.0003

Data Index: 8686 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1261078 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0572. Min Act: -0.0004

Data Index: 927068 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1278415 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0623. Min Act: -0.0003

Data Index: 68493 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0587. Min Act: -0.0003

Data Index: 840263 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0586. Min Act: -0.0003

Data Index: 419649 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0587. Min Act: -0.0003

Data Index: 779280 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1130257 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0580. Min Act: -0.0003

Data Index: 163501 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1012781 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0570. Min Act: -0.0003

Data Index: 101310 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0546. Min Act: -0.0003

Data Index: 1201733 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0565. Min Act: -0.0003

Data Index: 439400 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0511. Min Act: -0.0003

Data Index: 44797 (C4 (Web Text))

Max Activating Token Index: 791