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

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

Neuron 4132 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: 0.1509. Min Range: -0.1509

Max Act: 0.1509. Min Act: -0.0002

Data Index: 917537 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1464. Min Act: -0.0002

Data Index: 613242 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1468. Min Act: -0.0002

Data Index: 508758 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1255727 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1224. Min Act: -0.0002

Data Index: 870041 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1130. Min Act: -0.0002

Data Index: 342419 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1102. Min Act: -0.0002

Data Index: 810797 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1074. Min Act: -0.0002

Data Index: 635865 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1078091 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1151. Min Act: -0.0002

Data Index: 766 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1046. Min Act: -0.0002

Data Index: 808927 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1009148 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1090008 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1150. Min Act: -0.0002

Data Index: 693124 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1180. Min Act: -0.0002

Data Index: 896801 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1286. Min Act: -0.0002

Data Index: 659096 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1277. Min Act: -0.0002

Data Index: 1311735 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1118. Min Act: -0.0002

Data Index: 408940 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1123. Min Act: -0.0002

Data Index: 622572 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.1509. Min Range: -0.1509

Max Act: 0.1075. Min Act: -0.0002

Data Index: 529661 (C4 (Web Text))

Max Activating Token Index: 201