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

Dataset: The Pile

Neuron 4072 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: 0.1745. Min Range: -0.1745

Max Act: 0.1745. Min Act: -0.0000

Data Index: 494529 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1202243 (The Pile)

Max Activating Token Index: 786

Text #2

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1619. Min Act: -0.0000

Data Index: 33191 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1429. Min Act: -0.0000

Data Index: 340587 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1588. Min Act: -0.0000

Data Index: 602514 (The Pile)

Max Activating Token Index: 843

Text #5

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1421. Min Act: -0.0000

Data Index: 921114 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1395. Min Act: -0.0000

Data Index: 843741 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1367. Min Act: -0.0000

Data Index: 334104 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1386. Min Act: -0.0000

Data Index: 1686924 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1391. Min Act: -0.0000

Data Index: 966793 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1303. Min Act: -0.0000

Data Index: 601440 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1087513 (The Pile)

Max Activating Token Index: 588

Text #12

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1344. Min Act: -0.0000

Data Index: 176584 (The Pile)

Max Activating Token Index: 978

Text #13

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1047105 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1326. Min Act: -0.0000

Data Index: 585554 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1262730 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1417. Min Act: -0.0000

Data Index: 20663 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1238. Min Act: -0.0000

Data Index: 3748 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1403. Min Act: -0.0000

Data Index: 1839619 (The Pile)

Max Activating Token Index: 236

Text #19

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1282. Min Act: -0.0000

Data Index: 251032 (The Pile)

Max Activating Token Index: 116