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

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

Neuron 4466 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0002

Data Index: 999075 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1264. Min Act: -0.0002

Data Index: 139766 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1210. Min Act: -0.0002

Data Index: 44455 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1172. Min Act: -0.0002

Data Index: 941415 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1178. Min Act: -0.0003

Data Index: 735691 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1003052 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1137. Min Act: -0.0002

Data Index: 370705 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1136. Min Act: -0.0002

Data Index: 849078 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1098. Min Act: -0.0002

Data Index: 543929 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1110. Min Act: -0.0003

Data Index: 670816 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1122. Min Act: -0.0002

Data Index: 256102 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1104. Min Act: -0.0002

Data Index: 889133 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1221042 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1163982 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1086. Min Act: -0.0002

Data Index: 432289 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1271843 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1067. Min Act: -0.0002

Data Index: 822760 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1078. Min Act: -0.0002

Data Index: 531999 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1061. Min Act: -0.0002

Data Index: 64054 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1064. Min Act: -0.0002

Data Index: 172423 (C4 (Web Text))

Max Activating Token Index: 80