Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1687 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0003

Data Index: 598798 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0641. Min Act: -0.0003

Data Index: 445695 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0628. Min Act: -0.0003

Data Index: 460903 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0602. Min Act: -0.0003

Data Index: 332555 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0596. Min Act: -0.0004

Data Index: 172839 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1283682 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0618. Min Act: -0.0003

Data Index: 263652 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1103486 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0568. Min Act: -0.0003

Data Index: 263655 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0570. Min Act: -0.0003

Data Index: 1213034 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0567. Min Act: -0.0003

Data Index: 820073 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0568. Min Act: -0.0003

Data Index: 142566 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1057791 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0562. Min Act: -0.0004

Data Index: 426007 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0572. Min Act: -0.0003

Data Index: 5590 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0559. Min Act: -0.0003

Data Index: 941152 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0569. Min Act: -0.0003

Data Index: 113957 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1135083 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0551. Min Act: -0.0004

Data Index: 1120795 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0547. Min Act: -0.0004

Data Index: 903283 (C4 (Web Text))

Max Activating Token Index: 943