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

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

Neuron 4775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1358. Min Act: -0.0000

Data Index: 935510 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1129. Min Act: -0.0000

Data Index: 858833 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1141. Min Act: -0.0000

Data Index: 972979 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1188966 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1170. Min Act: -0.0000

Data Index: 647188 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1100. Min Act: -0.0000

Data Index: 816035 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1332371 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1129. Min Act: -0.0000

Data Index: 577943 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1061. Min Act: -0.0000

Data Index: 618007 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1103. Min Act: -0.0000

Data Index: 858981 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1308640 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1031. Min Act: -0.0000

Data Index: 223235 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0974. Min Act: -0.0000

Data Index: 199126 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0961. Min Act: -0.0000

Data Index: 159030 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0970. Min Act: -0.0000

Data Index: 519101 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1144173 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0970. Min Act: -0.0000

Data Index: 367501 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0939. Min Act: -0.0000

Data Index: 700813 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1167395 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1148436 (C4 (Web Text))

Max Activating Token Index: 445