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

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

Neuron 446 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: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0003

Data Index: 115312 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0686. Min Act: -0.0004

Data Index: 622726 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0694. Min Act: -0.0003

Data Index: 497810 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0678. Min Act: -0.0003

Data Index: 873895 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0642. Min Act: -0.0003

Data Index: 545199 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1319134 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0604. Min Act: -0.0003

Data Index: 632780 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0629. Min Act: -0.0003

Data Index: 726256 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0621. Min Act: -0.0003

Data Index: 124161 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1187851 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1281521 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0586. Min Act: -0.0004

Data Index: 539535 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0581. Min Act: -0.0004

Data Index: 561929 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1167933 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0583. Min Act: -0.0004

Data Index: 1265256 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0590. Min Act: -0.0004

Data Index: 527492 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1094621 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0584. Min Act: -0.0003

Data Index: 465086 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1175202 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0547. Min Act: -0.0003

Data Index: 719887 (C4 (Web Text))

Max Activating Token Index: 112