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

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

Neuron 3224 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2554. Min Act: -0.0001

Data Index: 514097 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2665. Min Act: -0.0001

Data Index: 639919 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.3047. Min Act: -0.0001

Data Index: 236912 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2020. Min Act: -0.0001

Data Index: 511704 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2161. Min Act: -0.0001

Data Index: 509017 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1973. Min Act: -0.0001

Data Index: 904720 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2002. Min Act: -0.0001

Data Index: 11280 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2044. Min Act: -0.0001

Data Index: 668014 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1295167 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1954. Min Act: -0.0001

Data Index: 274517 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2123. Min Act: -0.0001

Data Index: 394661 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1959. Min Act: -0.0001

Data Index: 656317 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1318530 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1931. Min Act: -0.0001

Data Index: 602434 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1873. Min Act: -0.0001

Data Index: 974330 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1077017 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1740. Min Act: -0.0001

Data Index: 623736 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1921. Min Act: -0.0001

Data Index: 358843 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1899. Min Act: -0.0001

Data Index: 351824 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1984. Min Act: -0.0001

Data Index: 687430 (C4 (Web Text))

Max Activating Token Index: 330