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

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

Neuron 2656 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1548862 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1511446 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1269. Min Act: -0.0001

Data Index: 1551272 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1513267 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1646716 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1361895 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1631111 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1586166 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1605682 (Python Code)

Max Activating Token Index: 697

Text #9

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1548524 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1510231 (Python Code)

Max Activating Token Index: 60

Text #11

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1401542 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1573798 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1469289 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1637395 (Python Code)

Max Activating Token Index: 772

Text #15

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1418420 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1590905 (Python Code)

Max Activating Token Index: 112

Text #17

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1415712 (Python Code)

Max Activating Token Index: 548

Text #18

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1571659 (Python Code)

Max Activating Token Index: 136

Text #19

Max Range: 0.1521. Min Range: -0.1521

Max Act: 0.1147. Min Act: -0.0001

Data Index: 1569525 (Python Code)

Max Activating Token Index: 915