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

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

Neuron 117 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: 0.1284. Min Range: -0.1284

Max Act: 0.1282. Min Act: -0.0003

Data Index: 985638 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1284. Min Act: -0.0003

Data Index: 490418 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1249. Min Act: -0.0003

Data Index: 1330872 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1242. Min Act: -0.0003

Data Index: 1358693 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1208. Min Act: -0.0003

Data Index: 446379 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1205. Min Act: -0.0003

Data Index: 506107 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1117. Min Act: -0.0003

Data Index: 441026 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1122. Min Act: -0.0003

Data Index: 1029099 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1190. Min Act: -0.0003

Data Index: 466022 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1099. Min Act: -0.0003

Data Index: 651427 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1035. Min Act: -0.0003

Data Index: 1334577 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0981. Min Act: -0.0003

Data Index: 330961 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1049. Min Act: -0.0004

Data Index: 1310277 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1033. Min Act: -0.0003

Data Index: 903133 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1042. Min Act: -0.0003

Data Index: 321777 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1033. Min Act: -0.0003

Data Index: 959989 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.0953. Min Act: -0.0003

Data Index: 426399 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1092. Min Act: -0.0003

Data Index: 749233 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1005. Min Act: -0.0003

Data Index: 862547 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1284. Min Range: -0.1284

Max Act: 0.1023. Min Act: -0.0003

Data Index: 454700 (C4 (Web Text))

Max Activating Token Index: 355