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

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

Neuron 28 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: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0003

Data Index: 1160209 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0511. Min Act: -0.0003

Data Index: 324658 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0442. Min Act: -0.0003

Data Index: 1058472 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1178024 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1266975 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1074695 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1049557 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0423. Min Act: -0.0003

Data Index: 625008 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0428. Min Act: -0.0003

Data Index: 636231 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0433. Min Act: -0.0003

Data Index: 213932 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0407. Min Act: -0.0003

Data Index: 110412 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1313994 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0411. Min Act: -0.0003

Data Index: 620898 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1310032 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0392. Min Act: -0.0003

Data Index: 2821 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1064795 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0399. Min Act: -0.0003

Data Index: 801123 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0396. Min Act: -0.0003

Data Index: 457726 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1295353 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0393. Min Act: -0.0003

Data Index: 135057 (C4 (Web Text))

Max Activating Token Index: 193