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

Dataset: The Pile

Neuron 3298 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: 0.3635. Min Range: -0.3635

Max Act: 0.3583. Min Act: -0.0000

Data Index: 829826 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1303278 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3635. Min Act: -0.0000

Data Index: 107430 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3517. Min Act: -0.0000

Data Index: 653132 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1417029 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3546. Min Act: -0.0000

Data Index: 886045 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1301000 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3399. Min Act: -0.0000

Data Index: 835644 (The Pile)

Max Activating Token Index: 904

Text #8

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3213. Min Act: -0.0000

Data Index: 609968 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3206. Min Act: -0.0000

Data Index: 411553 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2787. Min Act: -0.0000

Data Index: 1787071 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1599391 (The Pile)

Max Activating Token Index: 938

Text #12

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1765094 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2921. Min Act: -0.0000

Data Index: 537179 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1584062 (The Pile)

Max Activating Token Index: 811

Text #15

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2852. Min Act: -0.0000

Data Index: 230322 (The Pile)

Max Activating Token Index: 337

Text #16

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2158. Min Act: -0.0000

Data Index: 779937 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2684. Min Act: -0.0000

Data Index: 1365309 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1311266 (The Pile)

Max Activating Token Index: 998

Text #19

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3076. Min Act: -0.0000

Data Index: 1252522 (The Pile)

Max Activating Token Index: 431