Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2108 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1873. Min Act: -0.0000

Data Index: 404817 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1188072 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1566. Min Act: -0.0000

Data Index: 645675 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1420. Min Act: -0.0000

Data Index: 730832 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1435. Min Act: -0.0000

Data Index: 644492 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1335. Min Act: -0.0000

Data Index: 919575 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1308. Min Act: -0.0000

Data Index: 429772 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1269200 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1239. Min Act: -0.0000

Data Index: 603450 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1171. Min Act: 0.0000

Data Index: 139586 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1160. Min Act: 0.0000

Data Index: 1272715 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1130. Min Act: -0.0000

Data Index: 757438 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1157. Min Act: -0.0000

Data Index: 401645 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1112. Min Act: -0.0000

Data Index: 619304 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1317002 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1058. Min Act: -0.0000

Data Index: 459354 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1000221 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1064. Min Act: -0.0000

Data Index: 938241 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1113148 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1873. Min Range: -0.1873

Max Act: 0.0984. Min Act: -0.0000

Data Index: 156509 (C4 (Web Text))

Max Activating Token Index: 647