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

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

Neuron 3331 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0003

Data Index: 182422 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0685. Min Act: -0.0003

Data Index: 1018376 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1249309 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0651. Min Act: -0.0003

Data Index: 920224 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0608. Min Act: -0.0003

Data Index: 945255 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0593. Min Act: -0.0003

Data Index: 814642 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0614. Min Act: -0.0003

Data Index: 874972 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0632. Min Act: -0.0003

Data Index: 581176 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0631. Min Act: -0.0003

Data Index: 795295 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0611. Min Act: -0.0003

Data Index: 135360 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0598. Min Act: -0.0003

Data Index: 768136 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0578. Min Act: -0.0003

Data Index: 562614 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0583. Min Act: -0.0003

Data Index: 323059 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0578. Min Act: -0.0003

Data Index: 581120 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1047990 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0563. Min Act: -0.0003

Data Index: 791007 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0566. Min Act: -0.0003

Data Index: 1074981 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0576. Min Act: -0.0003

Data Index: 991251 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0564. Min Act: -0.0003

Data Index: 426850 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0560. Min Act: -0.0003

Data Index: 158870 (C4 (Web Text))

Max Activating Token Index: 150