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

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

Neuron 3263 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1484663 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1578671 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1431873 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1484761 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1544143 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1544651 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0199. Min Act: -0.0002

Data Index: 1554981 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1504701 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1446624 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1540552 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1569291 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1548375 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0195. Min Act: -0.0001

Data Index: 1486044 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1634300 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1495051 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0190. Min Act: -0.0002

Data Index: 1635866 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1479671 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1618098 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0189. Min Act: -0.0001

Data Index: 1600907 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0189. Min Act: -0.0001

Data Index: 1578207 (Python Code)

Max Activating Token Index: 1023