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

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

Neuron 2100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1376865 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.4606. Min Act: -0.0000

Data Index: 1401171 (Python Code)

Max Activating Token Index: 465

Text #2

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.3985. Min Act: -0.0000

Data Index: 1431716 (Python Code)

Max Activating Token Index: 800

Text #3

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.3574. Min Act: -0.0000

Data Index: 1364832 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1489800 (Python Code)

Max Activating Token Index: 736

Text #5

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.1168. Min Act: -0.0001

Data Index: 1599266 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.0300. Min Act: -0.0001

Data Index: 1371552 (Python Code)

Max Activating Token Index: 301

Text #7

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.0177. Min Act: -0.0000

Data Index: 1586314 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 1.5745. Min Range: -1.5745

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1625807 (Python Code)

Max Activating Token Index: 414

Text #9

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1479216 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9882. Min Act: -0.0001

Data Index: 1460727 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9224. Min Act: -0.0001

Data Index: 1423915 (Python Code)

Max Activating Token Index: 769

Text #12

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9721. Min Act: -0.0001

Data Index: 1406546 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1466386 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1613835 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1424210 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1391323 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1640008 (Python Code)

Max Activating Token Index: 95

Text #18

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1384007 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 1.5745. Min Range: -1.5745

Max Act: 0.8734. Min Act: -0.0001

Data Index: 1472593 (Python Code)

Max Activating Token Index: 817