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

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

Neuron 4707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1777. Min Act: -0.0002

Data Index: 105222 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1548. Min Act: -0.0002

Data Index: 267257 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1347. Min Act: -0.0002

Data Index: 517202 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1240. Min Act: -0.0002

Data Index: 949005 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1031489 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1302. Min Act: -0.0002

Data Index: 464454 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1249998 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1240. Min Act: -0.0002

Data Index: 1295498 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1278. Min Act: -0.0002

Data Index: 156020 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1355784 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1251. Min Act: -0.0002

Data Index: 651140 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1148. Min Act: -0.0002

Data Index: 231798 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1198. Min Act: -0.0002

Data Index: 42833 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1193. Min Act: -0.0002

Data Index: 386865 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1209. Min Act: -0.0002

Data Index: 111409 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1253122 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1087591 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1267988 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1121. Min Act: -0.0002

Data Index: 876314 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.1777. Min Range: -0.1777

Max Act: 0.1120. Min Act: -0.0002

Data Index: 153106 (C4 (Web Text))

Max Activating Token Index: 389