Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3340 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1059022 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0629. Min Act: -0.0002

Data Index: 726174 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1175313 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0597. Min Act: -0.0002

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0595. Min Act: -0.0002

Data Index: 206775 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0573. Min Act: -0.0002

Data Index: 842281 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0593. Min Act: -0.0002

Data Index: 33038 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0557. Min Act: -0.0002

Data Index: 550656 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0604. Min Act: -0.0002

Data Index: 404724 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0580. Min Act: -0.0002

Data Index: 113011 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0570. Min Act: -0.0002

Data Index: 773181 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0555. Min Act: -0.0002

Data Index: 147885 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0571. Min Act: -0.0002

Data Index: 324808 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0545. Min Act: -0.0002

Data Index: 260779 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0616. Min Act: -0.0002

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0568. Min Act: -0.0002

Data Index: 981682 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1120294 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0543. Min Act: -0.0002

Data Index: 577485 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1258664 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1043468 (C4 (Web Text))

Max Activating Token Index: 550