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

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

Neuron 5055 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0002

Data Index: 821553 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0477. Min Act: -0.0003

Data Index: 825889 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0472. Min Act: -0.0003

Data Index: 431458 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0441. Min Act: -0.0003

Data Index: 332402 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0453. Min Act: -0.0003

Data Index: 162915 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1101683 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0416. Min Act: -0.0003

Data Index: 967492 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0395. Min Act: -0.0003

Data Index: 992947 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0395. Min Act: -0.0003

Data Index: 1172158 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0387. Min Act: -0.0003

Data Index: 294289 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0392. Min Act: -0.0002

Data Index: 599057 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0385. Min Act: -0.0002

Data Index: 947246 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0387. Min Act: -0.0003

Data Index: 684219 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1205200 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1024818 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0379. Min Act: -0.0003

Data Index: 173886 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0374. Min Act: -0.0003

Data Index: 687402 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0374. Min Act: -0.0003

Data Index: 647594 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0376. Min Act: -0.0002

Data Index: 463677 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0369. Min Act: -0.0003

Data Index: 897914 (C4 (Web Text))

Max Activating Token Index: 775