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

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

Neuron 612 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0831. Min Act: -0.0002

Data Index: 294063 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0778. Min Act: -0.0002

Data Index: 871064 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0723. Min Act: -0.0002

Data Index: 522549 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1038661 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0743. Min Act: -0.0002

Data Index: 951606 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0767. Min Act: -0.0002

Data Index: 919588 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0686. Min Act: -0.0002

Data Index: 62187 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1323751 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0703. Min Act: -0.0002

Data Index: 710067 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0758. Min Act: -0.0002

Data Index: 710606 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0711. Min Act: -0.0002

Data Index: 672852 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0712. Min Act: -0.0002

Data Index: 1004371 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0684. Min Act: -0.0002

Data Index: 483794 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0706. Min Act: -0.0002

Data Index: 354157 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1272717 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1339077 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0691. Min Act: -0.0002

Data Index: 42426 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0674. Min Act: -0.0002

Data Index: 677981 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1354353 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0681. Min Act: -0.0002

Data Index: 543843 (C4 (Web Text))

Max Activating Token Index: 949