Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2209 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1427. Min Range: -1.1427

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1495049 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.1427. Min Range: -1.1427

Max Act: 1.1427. Min Act: -0.0000

Data Index: 1782531 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9112. Min Act: -0.0000

Data Index: 471711 (The Pile)

Max Activating Token Index: 585

Text #3

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1533709 (The Pile)

Max Activating Token Index: 880

Text #4

Max Range: 1.1427. Min Range: -1.1427

Max Act: 1.0302. Min Act: -0.0000

Data Index: 918448 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8911. Min Act: -0.0000

Data Index: 920639 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1709299 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1571357 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9318. Min Act: -0.0000

Data Index: 155121 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1359920 (The Pile)

Max Activating Token Index: 712

Text #10

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1895611 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9427. Min Act: -0.0000

Data Index: 789449 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8610. Min Act: -0.0000

Data Index: 594009 (The Pile)

Max Activating Token Index: 101

Text #13

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8811. Min Act: -0.0000

Data Index: 345044 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8437. Min Act: -0.0000

Data Index: 395926 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1865026 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.7960. Min Act: -0.0000

Data Index: 424626 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1740967 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8293. Min Act: -0.0000

Data Index: 208792 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 1.1427. Min Range: -1.1427

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1791907 (The Pile)

Max Activating Token Index: 89