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

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

Neuron 217 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: 0.0774. Min Range: -0.0774

Max Act: 0.0774. Min Act: -0.0005

Data Index: 739062 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0759. Min Act: -0.0005

Data Index: 325369 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0770. Min Act: -0.0005

Data Index: 6808 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0738. Min Act: -0.0005

Data Index: 90799 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0760. Min Act: -0.0005

Data Index: 726134 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0716. Min Act: -0.0005

Data Index: 260799 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0696. Min Act: -0.0005

Data Index: 1335138 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0733. Min Act: -0.0005

Data Index: 432813 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0662. Min Act: -0.0005

Data Index: 589264 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0676. Min Act: -0.0005

Data Index: 952512 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0675. Min Act: -0.0005

Data Index: 343852 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0682. Min Act: -0.0005

Data Index: 36707 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0617. Min Act: -0.0005

Data Index: 638433 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0693. Min Act: -0.0005

Data Index: 37363 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0662. Min Act: -0.0005

Data Index: 306485 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0695. Min Act: -0.0005

Data Index: 718536 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0706. Min Act: -0.0005

Data Index: 746582 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0635. Min Act: -0.0005

Data Index: 880592 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0659. Min Act: -0.0005

Data Index: 676880 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.0774. Min Range: -0.0774

Max Act: 0.0688. Min Act: -0.0005

Data Index: 814816 (C4 (Web Text))

Max Activating Token Index: 772