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

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

Neuron 4240 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.2849. Min Act: -0.0000

Data Index: 455952 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.3621. Min Act: -0.0000

Data Index: 294181 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.1368. Min Act: -0.0000

Data Index: 935485 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0457. Min Act: -0.0000

Data Index: 39457 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0362. Min Act: -0.0000

Data Index: 115275 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.9370. Min Act: -0.0000

Data Index: 365335 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0362. Min Act: -0.0000

Data Index: 56571 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1358129 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1017038 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.9210. Min Act: -0.0000

Data Index: 968682 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.3621. Min Range: -1.3621

Max Act: 1.0000. Min Act: -0.0000

Data Index: 606213 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1294692 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8690. Min Act: -0.0000

Data Index: 104533 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8638. Min Act: -0.0000

Data Index: 812889 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8709. Min Act: -0.0000

Data Index: 773773 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8789. Min Act: -0.0000

Data Index: 194479 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1230638 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1249366 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1196967 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 1.3621. Min Range: -1.3621

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1103146 (C4 (Web Text))

Max Activating Token Index: 128