Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1743577 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1624. Min Act: -0.0000

Data Index: 628297 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1610951 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1056308 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1329. Min Act: -0.0000

Data Index: 960660 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1334522 (The Pile)

Max Activating Token Index: 222

Text #6

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1408698 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1394125 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1495269 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1323. Min Act: -0.0000

Data Index: 1663993 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1685982 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1308704 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1372. Min Act: -0.0000

Data Index: 956155 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1222. Min Act: -0.0000

Data Index: 549665 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1170. Min Act: -0.0000

Data Index: 307216 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1895453 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1092662 (The Pile)

Max Activating Token Index: 1013

Text #17

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1206. Min Act: -0.0000

Data Index: 492267 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1295. Min Act: -0.0000

Data Index: 938353 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 0.1624. Min Range: -0.1624

Max Act: 0.1147. Min Act: -0.0000

Data Index: 291076 (The Pile)

Max Activating Token Index: 786