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

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

Neuron 417 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0812. Min Act: -0.0005

Data Index: 354543 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0743. Min Act: -0.0005

Data Index: 1185958 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0687. Min Act: -0.0005

Data Index: 737244 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0738. Min Act: -0.0005

Data Index: 955046 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0749. Min Act: -0.0005

Data Index: 1205438 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0757. Min Act: -0.0005

Data Index: 1334321 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0727. Min Act: -0.0005

Data Index: 243135 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0711. Min Act: -0.0004

Data Index: 856774 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0716. Min Act: -0.0005

Data Index: 577060 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0673. Min Act: -0.0005

Data Index: 445340 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0712. Min Act: -0.0004

Data Index: 1303450 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0639. Min Act: -0.0005

Data Index: 943744 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0669. Min Act: -0.0005

Data Index: 639484 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0712. Min Act: -0.0004

Data Index: 1234472 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0649. Min Act: -0.0005

Data Index: 641496 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0721. Min Act: -0.0005

Data Index: 1121305 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0674. Min Act: -0.0005

Data Index: 1178200 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0650. Min Act: -0.0005

Data Index: 605590 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0683. Min Act: -0.0005

Data Index: 74417 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 0.0812. Min Range: -0.0812

Max Act: 0.0703. Min Act: -0.0004

Data Index: 996518 (C4 (Web Text))

Max Activating Token Index: 429