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

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

Neuron 131 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: 0.1206. Min Range: -0.1206

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1552356 (Python Code)

Max Activating Token Index: 214

Text #1

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1195. Min Act: -0.0002

Data Index: 96719 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1172. Min Act: -0.0002

Data Index: 721597 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1198. Min Act: -0.0002

Data Index: 1519185 (Python Code)

Max Activating Token Index: 552

Text #4

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1065608 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1632424 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1140. Min Act: -0.0002

Data Index: 1508763 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1084. Min Act: -0.0002

Data Index: 74457 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1506075 (Python Code)

Max Activating Token Index: 793

Text #9

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1063. Min Act: -0.0002

Data Index: 1527923 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1597819 (Python Code)

Max Activating Token Index: 838

Text #11

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1594516 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1422987 (Python Code)

Max Activating Token Index: 370

Text #13

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1483770 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1448841 (Python Code)

Max Activating Token Index: 217

Text #15

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1438365 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1411931 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1645311 (Python Code)

Max Activating Token Index: 781

Text #18

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1435978 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1571779 (Python Code)

Max Activating Token Index: 683