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

Dataset: The Pile

Neuron 5034 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2677. Min Act: -0.0000

Data Index: 595637 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.2038. Min Act: -0.0000

Data Index: 390329 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1561266 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 1.2677. Min Range: -1.2677

Max Act: 1.1056. Min Act: -0.0000

Data Index: 403329 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9876. Min Act: -0.0000

Data Index: 699656 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.8136. Min Act: -0.0000

Data Index: 245613 (The Pile)

Max Activating Token Index: 933

Text #6

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1052906 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1076595 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9044. Min Act: -0.0000

Data Index: 968197 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1833533 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9248. Min Act: -0.0000

Data Index: 251648 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9468. Min Act: -0.0000

Data Index: 1168215 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1006624 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1600798 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9113. Min Act: -0.0000

Data Index: 414829 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.8964. Min Act: -0.0000

Data Index: 642566 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1087253 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.9044. Min Act: -0.0000

Data Index: 391987 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.7866. Min Act: -0.0000

Data Index: 760278 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 1.2677. Min Range: -1.2677

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1156724 (The Pile)

Max Activating Token Index: 421