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

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

Neuron 697 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: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0003

Data Index: 464366 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1142468 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0577. Min Act: -0.0003

Data Index: 329134 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0589. Min Act: -0.0003

Data Index: 607143 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0556. Min Act: -0.0003

Data Index: 615263 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0559. Min Act: -0.0002

Data Index: 379254 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0545. Min Act: -0.0002

Data Index: 307393 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0569. Min Act: -0.0003

Data Index: 145656 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0524. Min Act: -0.0003

Data Index: 805370 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0535. Min Act: -0.0003

Data Index: 316315 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0507. Min Act: -0.0003

Data Index: 69848 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0555. Min Act: -0.0002

Data Index: 616653 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0525. Min Act: -0.0003

Data Index: 613466 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0517. Min Act: -0.0003

Data Index: 271697 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0524. Min Act: -0.0002

Data Index: 543505 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0506. Min Act: -0.0003

Data Index: 901894 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0503. Min Act: -0.0002

Data Index: 283665 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0532. Min Act: -0.0003

Data Index: 553028 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0502. Min Act: -0.0002

Data Index: 480282 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1117509 (C4 (Web Text))

Max Activating Token Index: 1014