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

Dataset: The Pile

Neuron 1189 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: 0.8838. Min Range: -0.8838

Max Act: 0.8838. Min Act: 0.0000

Data Index: 538953 (The Pile)

Max Activating Token Index: 1015

Text #1

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1690416 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5380. Min Act: -0.0000

Data Index: 413408 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5072. Min Act: 0.0000

Data Index: 499965 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4573. Min Act: -0.0000

Data Index: 554980 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5205. Min Act: -0.0000

Data Index: 551011 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4671. Min Act: -0.0000

Data Index: 605585 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4940. Min Act: -0.0000

Data Index: 1900451 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1807133 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1485229 (The Pile)

Max Activating Token Index: 863

Text #10

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4842. Min Act: -0.0000

Data Index: 271087 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4700. Min Act: 0.0000

Data Index: 920600 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1019298 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1998357 (The Pile)

Max Activating Token Index: 556

Text #14

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1941105 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4423. Min Act: 0.0000

Data Index: 1632504 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4148. Min Act: -0.0000

Data Index: 741366 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4438. Min Act: -0.0000

Data Index: 778973 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1303335 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.8838. Min Range: -0.8838

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1394519 (The Pile)

Max Activating Token Index: 730