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

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

Neuron 1586 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1271. Min Act: -0.0002

Data Index: 657937 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1210. Min Act: -0.0002

Data Index: 476555 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0912. Min Act: -0.0002

Data Index: 732969 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1102. Min Act: -0.0002

Data Index: 65106 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1166. Min Act: -0.0002

Data Index: 734535 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1070. Min Act: -0.0002

Data Index: 57468 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1276. Min Act: -0.0002

Data Index: 861858 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0982. Min Act: -0.0002

Data Index: 273472 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1024. Min Act: -0.0002

Data Index: 344265 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1183. Min Act: -0.0002

Data Index: 772017 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0948. Min Act: -0.0002

Data Index: 794288 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0978. Min Act: -0.0002

Data Index: 179890 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1086. Min Act: -0.0002

Data Index: 1138554 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1000. Min Act: -0.0002

Data Index: 144476 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0833. Min Act: -0.0002

Data Index: 353488 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0859. Min Act: -0.0002

Data Index: 621111 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1067177 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1065247 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1100295 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.0805. Min Act: -0.0002

Data Index: 828586 (C4 (Web Text))

Max Activating Token Index: 265