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

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

Neuron 3007 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1172. Min Act: -0.0000

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1544148 (Python Code)

Max Activating Token Index: 846

Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1452610 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1087. Min Act: -0.0000

Data Index: 784377 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1144085 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1254. Min Act: -0.0000

Data Index: 724415 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1143. Min Act: -0.0000

Data Index: 367444 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1197. Min Act: -0.0000

Data Index: 303104 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1138. Min Act: -0.0000

Data Index: 629759 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1530672 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1648896 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1195. Min Act: -0.0000

Data Index: 96853 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1601820 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0984. Min Act: -0.0000

Data Index: 79893 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1416907 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1045. Min Act: -0.0000

Data Index: 587871 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1277503 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1281736 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1404318 (Python Code)

Max Activating Token Index: 128

Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1640954 (Python Code)

Max Activating Token Index: 154