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

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

Neuron 655 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0733. Min Act: -0.0005

Data Index: 346913 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0645. Min Act: -0.0005

Data Index: 867355 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0577. Min Act: -0.0005

Data Index: 1173218 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0586. Min Act: -0.0005

Data Index: 1153008 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0623. Min Act: -0.0005

Data Index: 980439 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0551. Min Act: -0.0005

Data Index: 69979 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0596. Min Act: -0.0005

Data Index: 270090 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0535. Min Act: -0.0005

Data Index: 273136 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0587. Min Act: -0.0005

Data Index: 1115614 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0551. Min Act: -0.0005

Data Index: 481349 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0559. Min Act: -0.0005

Data Index: 485358 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0572. Min Act: -0.0005

Data Index: 1319248 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0564. Min Act: -0.0005

Data Index: 615248 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0502. Min Act: -0.0005

Data Index: 626633 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0527. Min Act: -0.0005

Data Index: 285104 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0476. Min Act: -0.0005

Data Index: 957571 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0550. Min Act: -0.0005

Data Index: 1065252 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0511. Min Act: -0.0005

Data Index: 171395 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0515. Min Act: -0.0005

Data Index: 506086 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.0733. Min Range: -0.0733

Max Act: 0.0454. Min Act: -0.0005

Data Index: 507241 (C4 (Web Text))

Max Activating Token Index: 701