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

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

Neuron 5086 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: 0.8592. Min Range: -0.8592

Max Act: 0.8592. Min Act: -0.0002

Data Index: 878482 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.8574. Min Act: -0.0003

Data Index: 775922 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7902. Min Act: -0.0003

Data Index: 1285457 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7509. Min Act: -0.0003

Data Index: 639592 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7919. Min Act: -0.0003

Data Index: 895002 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7343. Min Act: -0.0003

Data Index: 220345 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7793. Min Act: -0.0003

Data Index: 582510 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7719. Min Act: -0.0002

Data Index: 995533 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7632. Min Act: -0.0002

Data Index: 371111 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7359. Min Act: -0.0003

Data Index: 360647 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7434. Min Act: -0.0003

Data Index: 1145801 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7535. Min Act: -0.0002

Data Index: 1039098 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7550. Min Act: -0.0003

Data Index: 586107 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7063. Min Act: -0.0003

Data Index: 1217014 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7274. Min Act: -0.0002

Data Index: 1183187 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7184. Min Act: -0.0002

Data Index: 237744 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7167. Min Act: -0.0003

Data Index: 1068541 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.6889. Min Act: -0.0003

Data Index: 626879 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7086. Min Act: -0.0003

Data Index: 13719 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.8592. Min Range: -0.8592

Max Act: 0.7076. Min Act: -0.0003

Data Index: 1266693 (C4 (Web Text))

Max Activating Token Index: 328