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

Dataset: The Pile

Neuron 3691 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.5306. Min Act: -0.0000

Data Index: 1947862 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.3579. Min Act: -0.0000

Data Index: 977237 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.1294. Min Act: -0.0000

Data Index: 613106 (The Pile)

Max Activating Token Index: 310

Text #3

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.2187. Min Act: -0.0000

Data Index: 77137 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1763275 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.1892. Min Act: -0.0000

Data Index: 487260 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1538423 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.0081. Min Act: -0.0000

Data Index: 432773 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.1366. Min Act: -0.0000

Data Index: 233864 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.0536. Min Act: -0.0000

Data Index: 952684 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1521696 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1979574 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9170. Min Act: -0.0000

Data Index: 38556 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9660. Min Act: -0.0000

Data Index: 695625 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9540. Min Act: -0.0000

Data Index: 734796 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9332. Min Act: -0.0000

Data Index: 1925373 (The Pile)

Max Activating Token Index: 108

Text #16

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.9391. Min Act: -0.0000

Data Index: 427216 (The Pile)

Max Activating Token Index: 187

Text #17

Max Range: 1.5306. Min Range: -1.5306

Max Act: 1.0098. Min Act: -0.0000

Data Index: 917224 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1415350 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 1.5306. Min Range: -1.5306

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1560055 (The Pile)

Max Activating Token Index: 237