Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 573 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0002

Data Index: 19059 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0451. Min Act: -0.0002

Data Index: 328699 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0482. Min Act: -0.0002

Data Index: 461 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0435. Min Act: -0.0002

Data Index: 271498 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0472. Min Act: -0.0002

Data Index: 298029 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0367. Min Act: -0.0002

Data Index: 949530 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1093758 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0386. Min Act: -0.0002

Data Index: 475336 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1110360 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1232922 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0433. Min Act: -0.0002

Data Index: 83069 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0441. Min Act: -0.0002

Data Index: 844044 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0406. Min Act: -0.0002

Data Index: 302077 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0417. Min Act: -0.0002

Data Index: 499778 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0399. Min Act: -0.0002

Data Index: 87074 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0389. Min Act: -0.0002

Data Index: 990363 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1124580 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0496. Min Act: -0.0002

Data Index: 346174 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0445. Min Act: -0.0002

Data Index: 254694 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0411. Min Act: -0.0002

Data Index: 989080 (C4 (Web Text))

Max Activating Token Index: 114