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

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

Neuron 555 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: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1355142 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0741. Min Act: -0.0003

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0714. Min Act: -0.0003

Data Index: 252706 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1255025 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0675. Min Act: -0.0003

Data Index: 500850 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0715. Min Act: -0.0003

Data Index: 51554 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1165835 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0666. Min Act: -0.0003

Data Index: 740807 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0652. Min Act: -0.0003

Data Index: 755831 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0628. Min Act: -0.0003

Data Index: 591629 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1194992 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1254373 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0650. Min Act: -0.0003

Data Index: 562410 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0633. Min Act: -0.0003

Data Index: 995788 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0627. Min Act: -0.0004

Data Index: 306609 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1220721 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0611. Min Act: -0.0003

Data Index: 112958 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0634. Min Act: -0.0003

Data Index: 355323 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0625. Min Act: -0.0003

Data Index: 211054 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0626. Min Act: -0.0003

Data Index: 464231 (C4 (Web Text))

Max Activating Token Index: 722