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

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

Neuron 448 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1459. Min Range: -2.1459

Max Act: 2.1459. Min Act: -0.0000

Data Index: 691713 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 2.1459. Min Range: -2.1459

Max Act: 2.0152. Min Act: -0.0000

Data Index: 550017 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1087041 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.9705. Min Act: -0.0000

Data Index: 1045660 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.8530. Min Act: -0.0000

Data Index: 603601 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.2351. Min Act: 0.0000

Data Index: 925654 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.1644. Min Act: -0.0000

Data Index: 613019 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1352466 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.1779. Min Act: -0.0000

Data Index: 183879 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0964. Min Act: 0.0001

Data Index: 596646 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.1597. Min Act: -0.0000

Data Index: 860634 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0870. Min Act: -0.0000

Data Index: 1130701 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0637. Min Act: -0.0000

Data Index: 303027 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0668. Min Act: -0.0000

Data Index: 82189 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0405. Min Act: -0.0000

Data Index: 937199 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 2.1459. Min Range: -2.1459

Max Act: 0.9728. Min Act: -0.0000

Data Index: 819219 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0068. Min Act: -0.0000

Data Index: 704868 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0331. Min Act: -0.0000

Data Index: 790155 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 2.1459. Min Range: -2.1459

Max Act: 1.0275. Min Act: -0.0000

Data Index: 291232 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 2.1459. Min Range: -2.1459

Max Act: 0.9737. Min Act: 0.0000

Data Index: 842601 (C4 (Web Text))

Max Activating Token Index: 968