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

Dataset: The Pile

Neuron 3399 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1995652 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5987. Min Act: -0.0000

Data Index: 447960 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1666350 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.5602. Min Act: -0.0000

Data Index: 102463 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4889. Min Act: -0.0000

Data Index: 807441 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4792. Min Act: -0.0000

Data Index: 506702 (The Pile)

Max Activating Token Index: 367

Text #6

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4774. Min Act: -0.0000

Data Index: 262008 (The Pile)

Max Activating Token Index: 452

Text #7

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4612. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4660. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4137. Min Act: -0.0000

Data Index: 628873 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1028340 (The Pile)

Max Activating Token Index: 99

Text #14

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1177227 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1674626 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4221. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.3340. Min Act: -0.0000

Data Index: 48337 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 0.6697. Min Range: -0.6697

Max Act: 0.4303. Min Act: -0.0000

Data Index: 309748 (The Pile)

Max Activating Token Index: 570