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

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

Neuron 2269 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1477. Min Act: -0.0001

Data Index: 141663 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1417. Min Act: -0.0001

Data Index: 995612 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1208572 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1122. Min Act: -0.0001

Data Index: 940951 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1276509 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1177. Min Act: -0.0001

Data Index: 337159 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1182. Min Act: -0.0001

Data Index: 551948 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1057. Min Act: -0.0001

Data Index: 337384 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1184. Min Act: -0.0001

Data Index: 733792 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1042526 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1116. Min Act: -0.0001

Data Index: 580069 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1082213 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1213469 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1103. Min Act: -0.0001

Data Index: 607607 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1063. Min Act: -0.0001

Data Index: 488 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1437025 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1018. Min Act: -0.0001

Data Index: 1225264 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1019. Min Act: -0.0001

Data Index: 672336 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1206214 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.1477. Min Range: -0.1477

Max Act: 0.1051. Min Act: -0.0001

Data Index: 218031 (C4 (Web Text))

Max Activating Token Index: 536