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

Dataset: The Pile

Neuron 1405 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: 1.4178. Min Range: -1.4178

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1878954 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2471. Min Act: -0.0000

Data Index: 170546 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3085. Min Act: -0.0000

Data Index: 510468 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1601483 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2249. Min Act: -0.0000

Data Index: 843112 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1986. Min Act: -0.0000

Data Index: 586634 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1877847 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1715767 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1381457 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2303. Min Act: -0.0000

Data Index: 435916 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1147. Min Act: -0.0000

Data Index: 116896 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1078834 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1919348 (The Pile)

Max Activating Token Index: 657

Text #13

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0730. Min Act: -0.0000

Data Index: 132785 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0710. Min Act: -0.0000

Data Index: 322361 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0995. Min Act: -0.0000

Data Index: 231189 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1048511 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1122543 (The Pile)

Max Activating Token Index: 445

Text #18

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.1184. Min Act: -0.0000

Data Index: 357206 (The Pile)

Max Activating Token Index: 918

Text #19

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0716. Min Act: -0.0000

Data Index: 814956 (The Pile)

Max Activating Token Index: 918