Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 314 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1517462 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1606643 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1486047 (Python Code)

Max Activating Token Index: 53

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1448997 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1541775 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1600346 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1429341 (Python Code)

Max Activating Token Index: 869

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1467538 (Python Code)

Max Activating Token Index: 554

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1508772 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8699. Min Act: -0.0001

Data Index: 1459925 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1647159 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1418335 (Python Code)

Max Activating Token Index: 70

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1483799 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1390686 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1368677 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1607934 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1627819 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1609794 (Python Code)

Max Activating Token Index: 927

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.6895. Min Act: -0.0000

Data Index: 1408894 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1628728 (Python Code)

Max Activating Token Index: 110