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

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

Neuron 22 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: 0.0440. Min Range: -0.0440

Max Act: 0.0422. Min Act: -0.0005

Data Index: 1620413 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0005

Data Index: 1479218 (Python Code)

Max Activating Token Index: 115

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0415. Min Act: -0.0005

Data Index: 1584678 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0412. Min Act: -0.0005

Data Index: 1414046 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0386. Min Act: -0.0005

Data Index: 1299775 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0387. Min Act: -0.0005

Data Index: 1358905 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0402. Min Act: -0.0005

Data Index: 465306 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0387. Min Act: -0.0005

Data Index: 1041463 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0391. Min Act: -0.0004

Data Index: 716299 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0355. Min Act: -0.0004

Data Index: 885768 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0362. Min Act: -0.0004

Data Index: 466039 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0373. Min Act: -0.0005

Data Index: 640447 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0374. Min Act: -0.0005

Data Index: 28851 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0378. Min Act: -0.0005

Data Index: 489918 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1068498 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0350. Min Act: -0.0005

Data Index: 118573 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0371. Min Act: -0.0004

Data Index: 479089 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0387. Min Act: -0.0005

Data Index: 914467 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1539154 (Python Code)

Max Activating Token Index: 303

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0375. Min Act: -0.0005

Data Index: 1149780 (C4 (Web Text))

Max Activating Token Index: 325