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

Dataset: The Pile

Neuron 4413 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: 0.8553. Min Range: -0.8553

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1453952 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8225. Min Act: -0.0000

Data Index: 373844 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7111. Min Act: -0.0000

Data Index: 738871 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1228171 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6826. Min Act: -0.0000

Data Index: 277590 (The Pile)

Max Activating Token Index: 424

Text #5

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7165. Min Act: -0.0000

Data Index: 1426567 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7488. Min Act: -0.0000

Data Index: 601952 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1563580 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1209454 (The Pile)

Max Activating Token Index: 529

Text #9

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5904. Min Act: -0.0000

Data Index: 391983 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7421. Min Act: -0.0000

Data Index: 603863 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6575. Min Act: -0.0000

Data Index: 399783 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6479. Min Act: -0.0000

Data Index: 154773 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1276262 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1450216 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6437. Min Act: -0.0000

Data Index: 830575 (The Pile)

Max Activating Token Index: 696

Text #16

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6141. Min Act: -0.0000

Data Index: 450783 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5891. Min Act: -0.0000

Data Index: 824288 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1377545 (The Pile)

Max Activating Token Index: 788

Text #19

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.5893. Min Act: -0.0000

Data Index: 394795 (The Pile)

Max Activating Token Index: 500