Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 984 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0004

Data Index: 1639312 (Python Code)

Max Activating Token Index: 179

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1241. Min Act: -0.0003

Data Index: 1653121 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1173. Min Act: -0.0003

Data Index: 1577540 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1158. Min Act: -0.0003

Data Index: 1515554 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1169. Min Act: -0.0003

Data Index: 1389300 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1163. Min Act: -0.0003

Data Index: 1448456 (Python Code)

Max Activating Token Index: 653

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1135. Min Act: -0.0003

Data Index: 1406094 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1106. Min Act: -0.0004

Data Index: 1522116 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1074. Min Act: -0.0003

Data Index: 946616 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1095. Min Act: -0.0003

Data Index: 1439789 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1100. Min Act: -0.0003

Data Index: 1369837 (Python Code)

Max Activating Token Index: 650

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1083. Min Act: -0.0003

Data Index: 1444800 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1587384 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1096. Min Act: -0.0003

Data Index: 1509220 (Python Code)

Max Activating Token Index: 617

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1035. Min Act: -0.0003

Data Index: 140450 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1102. Min Act: -0.0003

Data Index: 1373890 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1083. Min Act: -0.0003

Data Index: 1518838 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1027. Min Act: -0.0004

Data Index: 1448917 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1000. Min Act: -0.0004

Data Index: 1599931 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1016. Min Act: -0.0004

Data Index: 823426 (C4 (Web Text))

Max Activating Token Index: 668