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

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

Neuron 528 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: 0.0891. Min Range: -0.0891

Max Act: 0.0878. Min Act: -0.0002

Data Index: 125677 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0746. Min Act: -0.0003

Data Index: 302273 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0002

Data Index: 178545 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0772. Min Act: -0.0003

Data Index: 327929 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0806. Min Act: -0.0002

Data Index: 382395 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0779. Min Act: -0.0003

Data Index: 797985 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1177329 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0761. Min Act: -0.0003

Data Index: 1255887 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0704. Min Act: -0.0003

Data Index: 595048 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0698. Min Act: -0.0003

Data Index: 331045 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0699. Min Act: -0.0002

Data Index: 605279 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0756. Min Act: -0.0003

Data Index: 366842 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0672. Min Act: -0.0003

Data Index: 804947 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0696. Min Act: -0.0003

Data Index: 494661 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0709. Min Act: -0.0003

Data Index: 335706 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0757. Min Act: -0.0003

Data Index: 441498 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0720. Min Act: -0.0003

Data Index: 421616 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0699. Min Act: -0.0002

Data Index: 216904 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0695. Min Act: -0.0003

Data Index: 496403 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1051112 (C4 (Web Text))

Max Activating Token Index: 149