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

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

Neuron 2195 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: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1628701 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1192. Min Act: -0.0001

Data Index: 1539174 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1637158 (Python Code)

Max Activating Token Index: 578

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1597238 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1126. Min Act: -0.0001

Data Index: 1468553 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1488725 (Python Code)

Max Activating Token Index: 30

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1539309 (Python Code)

Max Activating Token Index: 478

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1534155 (Python Code)

Max Activating Token Index: 128

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1580719 (Python Code)

Max Activating Token Index: 44

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1464342 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1583096 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1538701 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1592070 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1389777 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1368940 (Python Code)

Max Activating Token Index: 490

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1504940 (Python Code)

Max Activating Token Index: 159

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1363901 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1645168 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1567487 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0824. Min Act: -0.0001

Data Index: 1475732 (Python Code)

Max Activating Token Index: 727