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

Dataset: The Pile

Neuron 971 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.1172. Min Act: -0.0000

Data Index: 710795 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1799557 (The Pile)

Max Activating Token Index: 317

Text #2

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.1096. Min Act: -0.0000

Data Index: 246879 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0981. Min Act: -0.0000

Data Index: 633660 (The Pile)

Max Activating Token Index: 249

Text #4

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0525. Min Act: -0.0000

Data Index: 906232 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0209. Min Act: -0.0000

Data Index: 907617 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0539. Min Act: -0.0000

Data Index: 831602 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0435. Min Act: -0.0000

Data Index: 759728 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1976117 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1074783 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9974. Min Act: -0.0000

Data Index: 200849 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1674764 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0430. Min Act: -0.0000

Data Index: 488424 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9074. Min Act: -0.0000

Data Index: 43104 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0801. Min Act: -0.0000

Data Index: 406165 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1983254 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1561570 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9765. Min Act: -0.0000

Data Index: 1277138 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 1.1501. Min Range: -1.1501

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1328824 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9478. Min Act: -0.0000

Data Index: 328716 (The Pile)

Max Activating Token Index: 155