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

Dataset: The Pile

Neuron 1943 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: 0.0000

Data Index: 874997 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1424. Min Act: 0.0000

Data Index: 1082619 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1349. Min Act: 0.0000

Data Index: 1239464 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1333. Min Act: 0.0000

Data Index: 237447 (The Pile)

Max Activating Token Index: 3

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1328. Min Act: 0.0001

Data Index: 867669 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1301. Min Act: 0.0001

Data Index: 37463 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1295. Min Act: -0.0000

Data Index: 98414 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1264. Min Act: 0.0000

Data Index: 877705 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1260. Min Act: -0.0000

Data Index: 173254 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1304. Min Act: 0.0000

Data Index: 1893304 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1250. Min Act: 0.0000

Data Index: 1496795 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1290. Min Act: 0.0000

Data Index: 1900934 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1244. Min Act: 0.0000

Data Index: 1873653 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1226. Min Act: -0.0000

Data Index: 228937 (The Pile)

Max Activating Token Index: 3

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1210. Min Act: 0.0000

Data Index: 725408 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1246. Min Act: -0.0000

Data Index: 709112 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1199. Min Act: -0.0000

Data Index: 736222 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1193. Min Act: 0.0000

Data Index: 1530551 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1167. Min Act: 0.0000

Data Index: 1047738 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1981661 (The Pile)

Max Activating Token Index: 1023