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

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

Neuron 2644 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0756. Min Act: -0.0001

Data Index: 250308 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0715. Min Act: -0.0001

Data Index: 414874 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0629. Min Act: -0.0001

Data Index: 21278 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0700. Min Act: -0.0001

Data Index: 265027 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0677. Min Act: -0.0001

Data Index: 80880 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1213255 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0701. Min Act: -0.0001

Data Index: 832495 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0686. Min Act: -0.0001

Data Index: 807823 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0656. Min Act: -0.0001

Data Index: 400894 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0672. Min Act: -0.0001

Data Index: 926459 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0631. Min Act: -0.0001

Data Index: 46979 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0653. Min Act: -0.0001

Data Index: 366145 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0644. Min Act: -0.0001

Data Index: 320466 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0598. Min Act: -0.0001

Data Index: 79273 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0603. Min Act: -0.0001

Data Index: 40032 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0582. Min Act: -0.0001

Data Index: 746337 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0644. Min Act: -0.0001

Data Index: 105425 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1116627 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1222516 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0756. Min Range: -0.0756

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1145066 (C4 (Web Text))

Max Activating Token Index: 231