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

Dataset: The Pile

Neuron 3842 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: 1.8044. Min Range: -1.8044

Max Act: 1.6271. Min Act: -0.0000

Data Index: 463339 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.8044. Min Act: -0.0000

Data Index: 180425 (The Pile)

Max Activating Token Index: 222

Text #2

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.6163. Min Act: -0.0000

Data Index: 568931 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.6490. Min Act: -0.0000

Data Index: 733310 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.4360. Min Act: -0.0000

Data Index: 1083687 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1913923 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1039487 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3413. Min Act: -0.0000

Data Index: 448539 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2032. Min Act: -0.0000

Data Index: 181893 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1327521 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1596. Min Act: -0.0000

Data Index: 731367 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1877. Min Act: -0.0000

Data Index: 459556 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2237. Min Act: -0.0000

Data Index: 282297 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1833967 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1124. Min Act: -0.0000

Data Index: 989670 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1317. Min Act: -0.0000

Data Index: 669645 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1465. Min Act: -0.0000

Data Index: 44072 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1391. Min Act: -0.0000

Data Index: 296080 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.0711. Min Act: -0.0000

Data Index: 1462755 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1403. Min Act: -0.0000

Data Index: 1386230 (The Pile)

Max Activating Token Index: 468