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

Dataset: The Pile

Neuron 4648 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.2049. Min Act: -0.0000

Data Index: 56993 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1921721 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1779348 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1375. Min Act: -0.0000

Data Index: 477103 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1257. Min Act: -0.0000

Data Index: 539913 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1038325 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1362926 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1266995 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1629666 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1722179 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1381209 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1222. Min Act: -0.0000

Data Index: 1410229 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1171. Min Act: -0.0000

Data Index: 959505 (The Pile)

Max Activating Token Index: 864

Text #13

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1178. Min Act: -0.0000

Data Index: 59764 (The Pile)

Max Activating Token Index: 551

Text #14

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1128. Min Act: -0.0000

Data Index: 369546 (The Pile)

Max Activating Token Index: 640

Text #15

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1162. Min Act: 0.0000

Data Index: 1811545 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1115. Min Act: -0.0000

Data Index: 80810 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1257. Min Act: -0.0000

Data Index: 562618 (The Pile)

Max Activating Token Index: 815

Text #18

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1120. Min Act: -0.0000

Data Index: 1016155 (The Pile)

Max Activating Token Index: 812

Text #19

Max Range: 0.2049. Min Range: -0.2049

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1442905 (The Pile)

Max Activating Token Index: 266