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

Dataset: The Pile

Neuron 1884 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.5696. Min Act: -0.0000

Data Index: 734799 (The Pile)

Max Activating Token Index: 882

Text #1

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.2436. Min Act: -0.0001

Data Index: 777304 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.4261. Min Act: -0.0000

Data Index: 334575 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1357208 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1657257 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0759. Min Act: -0.0000

Data Index: 1216922 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1112. Min Act: -0.0000

Data Index: 881492 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1628. Min Act: -0.0000

Data Index: 729122 (The Pile)

Max Activating Token Index: 22

Text #8

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1289353 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1177294 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0716. Min Act: -0.0000

Data Index: 903496 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1359. Min Act: -0.0000

Data Index: 97501 (The Pile)

Max Activating Token Index: 363

Text #12

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0946. Min Act: -0.0000

Data Index: 168968 (The Pile)

Max Activating Token Index: 335

Text #13

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0592. Min Act: -0.0000

Data Index: 964501 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0381. Min Act: -0.0000

Data Index: 723465 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1043. Min Act: -0.0000

Data Index: 308348 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1384. Min Act: -0.0000

Data Index: 239879 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.1348. Min Act: -0.0000

Data Index: 625314 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 1.5696. Min Range: -1.5696

Max Act: 1.0617. Min Act: -0.0000

Data Index: 966402 (The Pile)

Max Activating Token Index: 27

Text #19

Max Range: 1.5696. Min Range: -1.5696

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1696822 (The Pile)

Max Activating Token Index: 440