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

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

Neuron 1070 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: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1397454 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0246. Min Act: -0.0001

Data Index: 828130 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1402470 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1650076 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0225. Min Act: -0.0001

Data Index: 1410164 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1549500 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1438301 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1414896 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1509408 (Python Code)

Max Activating Token Index: 7

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1578730 (Python Code)

Max Activating Token Index: 84

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1361800 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0195. Min Act: -0.0001

Data Index: 410341 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1368882 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1490502 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0199. Min Act: -0.0001

Data Index: 716968 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0193. Min Act: -0.0001

Data Index: 1636931 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0198. Min Act: -0.0001

Data Index: 1375840 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1540885 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1649248 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1506449 (Python Code)

Max Activating Token Index: 12