Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 42 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1223. Min Act: -0.0003

Data Index: 1651491 (Python Code)

Max Activating Token Index: 903

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1243. Min Act: -0.0003

Data Index: 1595248 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0003

Data Index: 1412702 (Python Code)

Max Activating Token Index: 990

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1097. Min Act: -0.0003

Data Index: 1609813 (Python Code)

Max Activating Token Index: 50

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1051. Min Act: -0.0003

Data Index: 1546338 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1492527 (Python Code)

Max Activating Token Index: 268

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1422240 (Python Code)

Max Activating Token Index: 95

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1024. Min Act: -0.0003

Data Index: 1490471 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1096. Min Act: -0.0003

Data Index: 1551561 (Python Code)

Max Activating Token Index: 257

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1151. Min Act: -0.0003

Data Index: 1391638 (Python Code)

Max Activating Token Index: 623

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1024. Min Act: -0.0003

Data Index: 1546039 (Python Code)

Max Activating Token Index: 765

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0992. Min Act: -0.0003

Data Index: 1623852 (Python Code)

Max Activating Token Index: 898

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0998. Min Act: -0.0003

Data Index: 1561842 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0998. Min Act: -0.0003

Data Index: 1593263 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1497284 (Python Code)

Max Activating Token Index: 224

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1024. Min Act: -0.0003

Data Index: 1629870 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0852. Min Act: -0.0003

Data Index: 1648376 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1061. Min Act: -0.0003

Data Index: 1531905 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1469828 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1449048 (Python Code)

Max Activating Token Index: 81