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

Dataset: The Pile

Neuron 148 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: 0.9917. Min Range: -0.9917

Max Act: 0.9917. Min Act: -0.0000

Data Index: 583745 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8635. Min Act: -0.0000

Data Index: 868380 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1843861 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7946. Min Act: -0.0000

Data Index: 1412676 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1541990 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7766. Min Act: -0.0000

Data Index: 1765330 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6704. Min Act: -0.0000

Data Index: 447158 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1296014 (The Pile)

Max Activating Token Index: 319

Text #8

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7486. Min Act: -0.0000

Data Index: 637650 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7763. Min Act: -0.0000

Data Index: 13863 (The Pile)

Max Activating Token Index: 330

Text #10

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1475343 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1735857 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7530. Min Act: -0.0000

Data Index: 332372 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7234. Min Act: -0.0000

Data Index: 108456 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7368. Min Act: -0.0000

Data Index: 34199 (The Pile)

Max Activating Token Index: 428

Text #15

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1506225 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1197581 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.5608. Min Act: -0.0000

Data Index: 221088 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6725. Min Act: -0.0000

Data Index: 119573 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.9917. Min Range: -0.9917

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1920469 (The Pile)

Max Activating Token Index: 86