Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1654 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2671. Min Act: -0.0000

Data Index: 886961 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1076944 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0920. Min Act: -0.0000

Data Index: 187589 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1010608 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1197. Min Act: -0.0000

Data Index: 67626 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1207. Min Act: -0.0000

Data Index: 29921 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0732. Min Act: -0.0000

Data Index: 324476 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1190619 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0938. Min Act: -0.0000

Data Index: 454848 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0614. Min Act: -0.0000

Data Index: 541340 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0864. Min Act: -0.0000

Data Index: 197066 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0855. Min Act: -0.0000

Data Index: 692088 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0860. Min Act: -0.0000

Data Index: 482514 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1336337 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1342891 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0718. Min Act: -0.0000

Data Index: 296189 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0728. Min Act: -0.0000

Data Index: 127131 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0714. Min Act: -0.0000

Data Index: 101192 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1107570 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1158153 (C4 (Web Text))

Max Activating Token Index: 892