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

Dataset: The Pile

Neuron 715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1164022 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1691859 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3935. Min Act: -0.0000

Data Index: 747572 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.4021. Min Act: -0.0000

Data Index: 363598 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2018. Min Act: -0.0000

Data Index: 526183 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1853. Min Act: -0.0000

Data Index: 1539418 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2129. Min Act: -0.0000

Data Index: 162815 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2355. Min Act: -0.0000

Data Index: 442028 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1828537 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.0942. Min Act: -0.0000

Data Index: 1864149 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1869185 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2854. Min Act: -0.0000

Data Index: 51872 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1129464 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1039391 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 1.4603. Min Range: -1.4603

Max Act: 0.9866. Min Act: -0.0000

Data Index: 478650 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1119. Min Act: -0.0000

Data Index: 485987 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1805. Min Act: -0.0000

Data Index: 891815 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.1872. Min Act: -0.0000

Data Index: 333419 (The Pile)

Max Activating Token Index: 19

Text #18

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2248. Min Act: -0.0000

Data Index: 668753 (The Pile)

Max Activating Token Index: 256

Text #19

Max Range: 1.4603. Min Range: -1.4603

Max Act: 1.2397. Min Act: -0.0000

Data Index: 956890 (The Pile)

Max Activating Token Index: 559