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

Dataset: The Pile

Neuron 2061 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: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1984773 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1917252 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5844. Min Act: -0.0000

Data Index: 359011 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1729867 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5874. Min Act: -0.0000

Data Index: 124689 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5881. Min Act: -0.0000

Data Index: 875482 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1638369 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5464. Min Act: -0.0000

Data Index: 241802 (The Pile)

Max Activating Token Index: 834

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6170. Min Act: -0.0000

Data Index: 380450 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1013689 (The Pile)

Max Activating Token Index: 738

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1484344 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5290. Min Act: -0.0000

Data Index: 693276 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5472. Min Act: -0.0000

Data Index: 475797 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1467664 (The Pile)

Max Activating Token Index: 348

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5389. Min Act: -0.0000

Data Index: 797032 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5172. Min Act: 0.0000

Data Index: 1184314 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1172877 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5352. Min Act: -0.0000

Data Index: 48588 (The Pile)

Max Activating Token Index: 361

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4718. Min Act: -0.0000

Data Index: 387653 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4718. Min Act: -0.0000

Data Index: 633559 (The Pile)

Max Activating Token Index: 235