Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 630 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1421. Min Act: -0.0003

Data Index: 46630 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1343. Min Act: -0.0002

Data Index: 1639633 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1143175 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1221. Min Act: -0.0002

Data Index: 962715 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1456544 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1627554 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1404844 (Python Code)

Max Activating Token Index: 67

Text #7

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1086. Min Act: -0.0003

Data Index: 314014 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1610357 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1651265 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1421463 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1604303 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1065. Min Act: -0.0002

Data Index: 787127 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1049. Min Act: -0.0002

Data Index: 430427 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1566348 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1466293 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1490622 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1486745 (Python Code)

Max Activating Token Index: 161

Text #18

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1482009 (Python Code)

Max Activating Token Index: 735

Text #19

Max Range: 0.1421. Min Range: -0.1421

Max Act: 0.1015. Min Act: -0.0002

Data Index: 819698 (C4 (Web Text))

Max Activating Token Index: 899