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

Dataset: The Pile

Neuron 1127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1631155 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1986142 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1503. Min Act: -0.0000

Data Index: 494961 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1117743 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1429. Min Act: -0.0000

Data Index: 461010 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1472. Min Act: -0.0000

Data Index: 25226 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1406. Min Act: -0.0000

Data Index: 10507 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1771115 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1423. Min Act: -0.0000

Data Index: 77907 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1991209 (The Pile)

Max Activating Token Index: 95

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1224164 (The Pile)

Max Activating Token Index: 374

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1029174 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1182. Min Act: -0.0000

Data Index: 106476 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1832301 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1293. Min Act: -0.0000

Data Index: 183469 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1156701 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1599981 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1237. Min Act: -0.0000

Data Index: 48228 (The Pile)

Max Activating Token Index: 221

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1290. Min Act: -0.0000

Data Index: 584845 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1357. Min Act: -0.0000

Data Index: 607708 (The Pile)

Max Activating Token Index: 233