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

Dataset: The Pile

Neuron 2553 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.9130. Min Act: -0.0000

Data Index: 1282243 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 1.9130. Min Range: -1.9130

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1004385 (The Pile)

Max Activating Token Index: 485

Text #2

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1874052 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.9388. Min Act: 0.0000

Data Index: 118090 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.9561. Min Act: -0.0000

Data Index: 360502 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.9635. Min Act: -0.0000

Data Index: 696864 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8826. Min Act: -0.0000

Data Index: 760007 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1800203 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1111602 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1918705 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8744. Min Act: -0.0000

Data Index: 996363 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8367. Min Act: -0.0000

Data Index: 242378 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1413668 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8497. Min Act: -0.0000

Data Index: 908064 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.8517. Min Act: 0.0000

Data Index: 631451 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1752394 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1957120 (The Pile)

Max Activating Token Index: 275

Text #17

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.7414. Min Act: -0.0000

Data Index: 84379 (The Pile)

Max Activating Token Index: 695

Text #18

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1933749 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 1.9130. Min Range: -1.9130

Max Act: 0.7391. Min Act: -0.0000

Data Index: 76012 (The Pile)

Max Activating Token Index: 795