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

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

Neuron 1068 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: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0002

Data Index: 972437 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0511. Min Act: -0.0002

Data Index: 979551 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0522. Min Act: -0.0002

Data Index: 999249 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0493. Min Act: -0.0001

Data Index: 176195 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0498. Min Act: -0.0002

Data Index: 692211 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0495. Min Act: -0.0002

Data Index: 339177 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1110086 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0467. Min Act: -0.0002

Data Index: 381624 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0445. Min Act: -0.0002

Data Index: 961729 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0414. Min Act: -0.0002

Data Index: 99977 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0425. Min Act: -0.0002

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0418. Min Act: -0.0002

Data Index: 952218 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0433. Min Act: -0.0002

Data Index: 841658 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0411. Min Act: -0.0002

Data Index: 116425 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0408. Min Act: -0.0001

Data Index: 159984 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0399. Min Act: -0.0002

Data Index: 386192 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1337682 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0406. Min Act: -0.0002

Data Index: 680610 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0387. Min Act: -0.0002

Data Index: 837225 (C4 (Web Text))

Max Activating Token Index: 151