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

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

Neuron 4791 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1201995 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0106. Min Act: -0.0003

Data Index: 865664 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1093530 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1026022 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0103. Min Act: -0.0003

Data Index: 1022770 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0003

Data Index: 545391 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0003

Data Index: 987427 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0101. Min Act: -0.0003

Data Index: 345721 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0003

Data Index: 792480 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0003

Data Index: 1261114 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0099. Min Act: -0.0003

Data Index: 954909 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0097. Min Act: -0.0003

Data Index: 1292398 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1486303 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1637316 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0003

Data Index: 1009000 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1541992 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0092. Min Act: -0.0003

Data Index: 267092 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1385383 (Python Code)

Max Activating Token Index: 213

Text #18

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0003

Data Index: 553972 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.0111. Min Range: -0.0111

Max Act: 0.0091. Min Act: -0.0003

Data Index: 423089 (C4 (Web Text))

Max Activating Token Index: 563