Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0004

Data Index: 140505 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1443. Min Act: -0.0003

Data Index: 865356 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1341. Min Act: -0.0003

Data Index: 709161 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1297. Min Act: -0.0003

Data Index: 524569 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1264. Min Act: -0.0003

Data Index: 1014830 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1202. Min Act: -0.0003

Data Index: 631164 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1226. Min Act: -0.0003

Data Index: 975694 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1190. Min Act: -0.0004

Data Index: 1087400 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1172. Min Act: -0.0003

Data Index: 597051 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1152. Min Act: -0.0003

Data Index: 834178 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1091. Min Act: -0.0003

Data Index: 234278 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1137. Min Act: -0.0003

Data Index: 224571 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1117. Min Act: -0.0003

Data Index: 1351131 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1113. Min Act: -0.0003

Data Index: 959975 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1144. Min Act: -0.0003

Data Index: 1077252 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1132. Min Act: -0.0003

Data Index: 992362 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1126. Min Act: -0.0003

Data Index: 245262 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1126. Min Act: -0.0004

Data Index: 1169406 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1083. Min Act: -0.0003

Data Index: 527995 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1095. Min Act: -0.0003

Data Index: 305778 (C4 (Web Text))

Max Activating Token Index: 866