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

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

Neuron 337 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: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 787104 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0652. Min Act: -0.0002

Data Index: 284931 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0659. Min Act: -0.0003

Data Index: 455309 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0654. Min Act: -0.0004

Data Index: 279489 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 94981 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0628. Min Act: -0.0002

Data Index: 21419 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0638. Min Act: -0.0002

Data Index: 201517 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0620. Min Act: -0.0002

Data Index: 828289 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0640. Min Act: -0.0003

Data Index: 509295 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0606. Min Act: -0.0003

Data Index: 362202 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0615. Min Act: -0.0003

Data Index: 35509 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0600. Min Act: -0.0004

Data Index: 190073 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0600. Min Act: -0.0003

Data Index: 56202 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1271424 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0582. Min Act: -0.0003

Data Index: 402268 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0595. Min Act: -0.0003

Data Index: 204264 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0585. Min Act: -0.0003

Data Index: 914456 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0552. Min Act: -0.0004

Data Index: 1347283 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0576. Min Act: -0.0003

Data Index: 12031 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1179947 (C4 (Web Text))

Max Activating Token Index: 909