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

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

Neuron 1943 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1406012 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1619047 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1503723 (Python Code)

Max Activating Token Index: 180

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1455951 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1606138 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1534566 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1561394 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1434163 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1436478 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1490939 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1471116 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1385812 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1391660 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1572833 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1636403 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1498540 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1413658 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1572421 (Python Code)

Max Activating Token Index: 163

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1570782 (Python Code)

Max Activating Token Index: 501

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1612697 (Python Code)

Max Activating Token Index: 755