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

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

Neuron 3441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0243. Min Act: -0.0001

Data Index: 535321 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0399. Min Act: -0.0001

Data Index: 682463 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.0984. Min Range: -1.0984

Max Act: 1.0984. Min Act: -0.0001

Data Index: 1194313 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9460. Min Act: -0.0002

Data Index: 991223 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9421. Min Act: -0.0001

Data Index: 202252 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8467. Min Act: -0.0002

Data Index: 1150968 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9099. Min Act: -0.0002

Data Index: 173247 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9023. Min Act: -0.0001

Data Index: 108861 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8745. Min Act: -0.0002

Data Index: 72339 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.9041. Min Act: -0.0001

Data Index: 726711 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8928. Min Act: -0.0002

Data Index: 15500 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8483. Min Act: -0.0001

Data Index: 52144 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8619. Min Act: -0.0001

Data Index: 968068 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8848. Min Act: -0.0002

Data Index: 590105 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8635. Min Act: -0.0001

Data Index: 1214696 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8708. Min Act: -0.0002

Data Index: 973028 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8528. Min Act: -0.0002

Data Index: 857488 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1133041 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8324. Min Act: -0.0001

Data Index: 1202799 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.0984. Min Range: -1.0984

Max Act: 0.8353. Min Act: -0.0002

Data Index: 1157326 (C4 (Web Text))

Max Activating Token Index: 31