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

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

Neuron 3953 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1323. Min Act: -0.0003

Data Index: 1254307 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1370. Min Act: -0.0003

Data Index: 1194239 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1263. Min Act: -0.0003

Data Index: 9398 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1258. Min Act: -0.0003

Data Index: 990051 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1256. Min Act: -0.0003

Data Index: 208838 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1214. Min Act: -0.0003

Data Index: 541671 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1219. Min Act: -0.0003

Data Index: 756797 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1104. Min Act: -0.0003

Data Index: 1097155 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1139. Min Act: -0.0003

Data Index: 393198 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1133. Min Act: -0.0002

Data Index: 796921 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1129. Min Act: -0.0003

Data Index: 1044521 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1065. Min Act: -0.0003

Data Index: 275625 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1093. Min Act: -0.0003

Data Index: 35360 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1081. Min Act: -0.0003

Data Index: 430465 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1029. Min Act: -0.0002

Data Index: 793546 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1029. Min Act: -0.0003

Data Index: 204379 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1068. Min Act: -0.0003

Data Index: 294711 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1112. Min Act: -0.0003

Data Index: 1231567 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1057. Min Act: -0.0003

Data Index: 918450 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.1370. Min Range: -0.1370

Max Act: 0.1048. Min Act: -0.0003

Data Index: 96636 (C4 (Web Text))

Max Activating Token Index: 130