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

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

Neuron 3273 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: 0.0551. Min Range: -0.0551

Max Act: 0.0551. Min Act: -0.0003

Data Index: 519702 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1314201 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0450. Min Act: -0.0003

Data Index: 953310 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0377. Min Act: -0.0003

Data Index: 446875 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0374. Min Act: -0.0002

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0361. Min Act: -0.0002

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0359. Min Act: -0.0002

Data Index: 549630 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0359. Min Act: -0.0003

Data Index: 649906 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1526909 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1237496 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1237038 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0367. Min Act: -0.0003

Data Index: 377368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0343. Min Act: -0.0002

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1402730 (Python Code)

Max Activating Token Index: 529

Text #14

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0364. Min Act: -0.0002

Data Index: 233972 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0374. Min Act: -0.0002

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1123909 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1061549 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0551. Min Range: -0.0551

Max Act: 0.0336. Min Act: -0.0003

Data Index: 899365 (C4 (Web Text))

Max Activating Token Index: 342