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

Dataset: The Pile

Neuron 3407 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: 0.5370. Min Range: -0.5370

Max Act: 0.5370. Min Act: -0.0000

Data Index: 816758 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1679946 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1988946 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1358749 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1005093 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4769. Min Act: -0.0000

Data Index: 931096 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1829625 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4566. Min Act: -0.0000

Data Index: 596901 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1016462 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1834092 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1670429 (The Pile)

Max Activating Token Index: 985

Text #11

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1803139 (The Pile)

Max Activating Token Index: 344

Text #12

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1855362 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4069. Min Act: -0.0000

Data Index: 126259 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4168. Min Act: -0.0000

Data Index: 194734 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4441. Min Act: -0.0000

Data Index: 519500 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1652729 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1532486 (The Pile)

Max Activating Token Index: 339

Text #18

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.3790. Min Act: -0.0000

Data Index: 1095323 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 0.5370. Min Range: -0.5370

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1326242 (The Pile)

Max Activating Token Index: 249