Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1262 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1413276 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0642. Min Act: -0.0002

Data Index: 105970 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1500691 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0628. Min Act: -0.0002

Data Index: 36738 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0602. Min Act: -0.0002

Data Index: 679331 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1645765 (Python Code)

Max Activating Token Index: 231

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0597. Min Act: -0.0002

Data Index: 807946 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1337580 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0565. Min Act: -0.0002

Data Index: 89110 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1177285 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0002

Data Index: 184227 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0570. Min Act: -0.0002

Data Index: 552132 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0575. Min Act: -0.0002

Data Index: 588217 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0555. Min Act: -0.0002

Data Index: 404783 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0555. Min Act: -0.0002

Data Index: 14906 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1357950 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0529. Min Act: -0.0002

Data Index: 365331 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0500. Min Act: -0.0002

Data Index: 865903 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0582. Min Act: -0.0002

Data Index: 672764 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1445417 (Python Code)

Max Activating Token Index: 200