Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 227 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1478603 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1501988 (Python Code)

Max Activating Token Index: 851

Text #2

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1460893 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1493215 (Python Code)

Max Activating Token Index: 944

Text #4

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1572144 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1649206 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1391430 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1456343 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1366090 (Python Code)

Max Activating Token Index: 500

Text #9

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1500743 (Python Code)

Max Activating Token Index: 939

Text #10

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1654277 (Python Code)

Max Activating Token Index: 55

Text #11

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1452634 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1105. Min Act: -0.0002

Data Index: 1626441 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1556072 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1593244 (Python Code)

Max Activating Token Index: 637

Text #15

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1512886 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1432063 (Python Code)

Max Activating Token Index: 403

Text #17

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1569343 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1367535 (Python Code)

Max Activating Token Index: 766

Text #19

Max Range: 0.1390. Min Range: -0.1390

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1500749 (Python Code)

Max Activating Token Index: 12