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

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

Neuron 3663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1256. Min Act: -0.0002

Data Index: 790215 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1154. Min Act: -0.0002

Data Index: 1244454 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1276245 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1570692 (Python Code)

Max Activating Token Index: 57

Text #4

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1051. Min Act: -0.0002

Data Index: 80117 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1122. Min Act: -0.0002

Data Index: 629893 (C4 (Web Text))

Max Activating Token Index: 321

Text #6

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1169. Min Act: -0.0002

Data Index: 5431 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1127. Min Act: -0.0002

Data Index: 967744 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1650533 (Python Code)

Max Activating Token Index: 262

Text #9

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1057. Min Act: -0.0002

Data Index: 16735 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1125. Min Act: -0.0002

Data Index: 569665 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1123. Min Act: -0.0002

Data Index: 610186 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1043. Min Act: -0.0002

Data Index: 615080 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1061320 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1113748 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1002. Min Act: -0.0002

Data Index: 230801 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1393497 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1616747 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1052. Min Act: -0.0002

Data Index: 1481133 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1084. Min Act: -0.0002

Data Index: 1382652 (Python Code)

Max Activating Token Index: 967