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

Dataset: The Pile

Neuron 3513 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: 1.4664. Min Range: -1.4664

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1228716 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.4664. Min Act: -0.0000

Data Index: 1968227 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1923389 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3510. Min Act: -0.0000

Data Index: 1667228 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1526018 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.3234. Min Act: -0.0000

Data Index: 76009 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2305. Min Act: -0.0000

Data Index: 495331 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1445339 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.1477. Min Act: -0.0000

Data Index: 341733 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1543008 (The Pile)

Max Activating Token Index: 603

Text #10

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.1064. Min Act: -0.0000

Data Index: 863681 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0841. Min Act: -0.0000

Data Index: 588622 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0276. Min Act: -0.0000

Data Index: 425837 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1358727 (The Pile)

Max Activating Token Index: 334

Text #14

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.1033. Min Act: -0.0000

Data Index: 540805 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0829. Min Act: -0.0000

Data Index: 491786 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.4664. Min Range: -1.4664

Max Act: 1.0156. Min Act: -0.0000

Data Index: 745310 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.9745. Min Act: -0.0000

Data Index: 601867 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.8826. Min Act: -0.0000

Data Index: 341378 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 1.4664. Min Range: -1.4664

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1116647 (The Pile)

Max Activating Token Index: 965