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

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

Neuron 2649 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: 0.1251. Min Range: -0.1251

Max Act: 0.1251. Min Act: -0.0001

Data Index: 987992 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1102. Min Act: -0.0001

Data Index: 542440 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1189077 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0986. Min Act: -0.0001

Data Index: 395782 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1144. Min Act: -0.0001

Data Index: 696179 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1049. Min Act: -0.0001

Data Index: 996267 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1050458 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1048. Min Act: -0.0001

Data Index: 479164 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1249534 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0978. Min Act: -0.0001

Data Index: 737595 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1083. Min Act: -0.0001

Data Index: 499700 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1532347 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1347767 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1479956 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1256556 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1076516 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0997. Min Act: -0.0001

Data Index: 625377 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1057. Min Act: -0.0001

Data Index: 972367 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.0993. Min Act: -0.0001

Data Index: 161662 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.1251. Min Range: -0.1251

Max Act: 0.1007. Min Act: -0.0001

Data Index: 357570 (C4 (Web Text))

Max Activating Token Index: 475