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

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

Neuron 3729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0000

Data Index: 889602 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1563146 (Python Code)

Max Activating Token Index: 731

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1207856 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1430889 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1547429 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1417448 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1152. Min Act: -0.0000

Data Index: 272662 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1095. Min Act: -0.0000

Data Index: 323567 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1127. Min Act: -0.0000

Data Index: 261203 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1591469 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1456220 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1227629 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1283429 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1025. Min Act: -0.0001

Data Index: 1372869 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1556634 (Python Code)

Max Activating Token Index: 876

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1039. Min Act: -0.0000

Data Index: 36610 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1038. Min Act: -0.0001

Data Index: 828460 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1317503 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1579282 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1556255 (Python Code)

Max Activating Token Index: 878