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

Dataset: The Pile

Neuron 684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.4768. Min Act: -0.0000

Data Index: 424194 (The Pile)

Max Activating Token Index: 903

Text #1

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.5830. Min Act: -0.0000

Data Index: 1365744 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.4524. Min Act: -0.0000

Data Index: 892050 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1557340 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1586222 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.2337. Min Act: -0.0000

Data Index: 91962 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.3900. Min Act: -0.0000

Data Index: 11268 (The Pile)

Max Activating Token Index: 384

Text #7

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.4725. Min Act: -0.0000

Data Index: 1350766 (The Pile)

Max Activating Token Index: 729

Text #8

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1901168 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1749988 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1943826 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.1248. Min Act: -0.0000

Data Index: 907523 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1050923 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.2358. Min Act: -0.0000

Data Index: 887351 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.4561. Min Act: -0.0000

Data Index: 766351 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.1092. Min Act: -0.0000

Data Index: 914802 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.2847. Min Act: -0.0000

Data Index: 118346 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1999234 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.1593. Min Act: -0.0000

Data Index: 305531 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 1.5830. Min Range: -1.5830

Max Act: 1.2339. Min Act: -0.0000

Data Index: 544862 (The Pile)

Max Activating Token Index: 250