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

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

Neuron 4867 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1092321 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0635. Min Act: -0.0002

Data Index: 388872 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0654. Min Act: -0.0002

Data Index: 226854 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0633. Min Act: -0.0002

Data Index: 919972 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0619. Min Act: -0.0002

Data Index: 196700 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1183743 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0638. Min Act: -0.0002

Data Index: 425977 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0623. Min Act: -0.0002

Data Index: 933098 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0609. Min Act: -0.0002

Data Index: 601680 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0597. Min Act: -0.0002

Data Index: 253453 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0587. Min Act: -0.0002

Data Index: 579987 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1122004 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0583. Min Act: -0.0002

Data Index: 919140 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0583. Min Act: -0.0002

Data Index: 71146 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1201657 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0548. Min Act: -0.0002

Data Index: 608767 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0547. Min Act: -0.0002

Data Index: 479662 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0568. Min Act: -0.0002

Data Index: 807572 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0582. Min Act: -0.0002

Data Index: 430946 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0560. Min Act: -0.0002

Data Index: 690587 (C4 (Web Text))

Max Activating Token Index: 354