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

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

Neuron 3115 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1045068 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0859. Min Act: -0.0000

Data Index: 189439 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1264751 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0849. Min Act: -0.0000

Data Index: 94519 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1279700 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0765. Min Act: -0.0000

Data Index: 1292965 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1231628 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1224582 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0736. Min Act: -0.0000

Data Index: 281212 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0789. Min Act: -0.0000

Data Index: 391018 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1009398 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1503697 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0722. Min Act: -0.0001

Data Index: 48058 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1162379 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0736. Min Act: -0.0000

Data Index: 496166 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0692. Min Act: -0.0000

Data Index: 740488 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0692. Min Act: -0.0000

Data Index: 364555 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0695. Min Act: -0.0001

Data Index: 1311780 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0666. Min Act: -0.0000

Data Index: 574167 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.1528. Min Range: -0.1528

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1136815 (C4 (Web Text))

Max Activating Token Index: 236