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

Dataset: The Pile

Neuron 1333 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: 0.4209. Min Range: -0.4209

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1598266 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3958. Min Act: -0.0000

Data Index: 455033 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3841. Min Act: -0.0000

Data Index: 300680 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1273549 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1761590 (The Pile)

Max Activating Token Index: 875

Text #5

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1259225 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3866. Min Act: -0.0000

Data Index: 424549 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1138051 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3792. Min Act: -0.0000

Data Index: 906736 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3783. Min Act: -0.0000

Data Index: 1402245 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1670459 (The Pile)

Max Activating Token Index: 304

Text #11

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1437953 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3515. Min Act: -0.0000

Data Index: 186223 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3511. Min Act: -0.0000

Data Index: 516162 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1816420 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1783021 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1813966 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1989834 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3563. Min Act: -0.0000

Data Index: 177591 (The Pile)

Max Activating Token Index: 943

Text #19

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3627. Min Act: -0.0000

Data Index: 769834 (The Pile)

Max Activating Token Index: 457