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

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

Neuron 1590 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: 1.0264. Min Range: -1.0264

Max Act: 1.0056. Min Act: -0.0000

Data Index: 917178 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1334368 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9978. Min Act: -0.0000

Data Index: 863816 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.0264. Min Range: -1.0264

Max Act: 1.0264. Min Act: -0.0000

Data Index: 371918 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9427. Min Act: -0.0000

Data Index: 743390 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9292. Min Act: -0.0000

Data Index: 863013 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8468. Min Act: -0.0000

Data Index: 114196 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1350085 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9403. Min Act: -0.0000

Data Index: 461122 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1228865 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8558. Min Act: -0.0000

Data Index: 111817 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1121102 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8496. Min Act: -0.0000

Data Index: 227812 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8484. Min Act: -0.0000

Data Index: 203008 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1100578 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8360. Min Act: -0.0000

Data Index: 391355 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8095. Min Act: -0.0000

Data Index: 856059 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8436. Min Act: -0.0000

Data Index: 277019 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7405. Min Act: -0.0000

Data Index: 835818 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1065040 (C4 (Web Text))

Max Activating Token Index: 747