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

Dataset: The Pile

Neuron 3212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1390. Min Act: -0.0000

Data Index: 235617 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0000

Data Index: 95645 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1489799 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1687899 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1573489 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0918. Min Act: -0.0000

Data Index: 476520 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1884819 (The Pile)

Max Activating Token Index: 637

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1030400 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0862. Min Act: -0.0000

Data Index: 278406 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0824. Min Act: -0.0000

Data Index: 518684 (The Pile)

Max Activating Token Index: 363

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1515055 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0796. Min Act: -0.0000

Data Index: 305744 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0812. Min Act: -0.0000

Data Index: 535318 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0705. Min Act: -0.0000

Data Index: 1246959 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1600410 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0731. Min Act: -0.0000

Data Index: 934879 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1940889 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0886. Min Act: -0.0000

Data Index: 18900 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1246376 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0793. Min Act: -0.0000

Data Index: 906374 (The Pile)

Max Activating Token Index: 797