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

Dataset: The Pile

Neuron 3652 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: 0.7397. Min Range: -0.7397

Max Act: 0.7397. Min Act: -0.0000

Data Index: 467360 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1379915 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7309. Min Act: -0.0000

Data Index: 263340 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6874. Min Act: -0.0000

Data Index: 755659 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7079. Min Act: -0.0000

Data Index: 16634 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6777. Min Act: -0.0000

Data Index: 285519 (The Pile)

Max Activating Token Index: 238

Text #6

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6886. Min Act: -0.0000

Data Index: 535829 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6800. Min Act: -0.0000

Data Index: 386386 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1818446 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6602. Min Act: -0.0000

Data Index: 1660898 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6344. Min Act: -0.0000

Data Index: 826487 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1802681 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6730. Min Act: -0.0000

Data Index: 930711 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6798. Min Act: -0.0000

Data Index: 357491 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6739. Min Act: -0.0000

Data Index: 655865 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6482. Min Act: -0.0000

Data Index: 598670 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6467. Min Act: -0.0000

Data Index: 222710 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1376685 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6682. Min Act: -0.0000

Data Index: 248710 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6175. Min Act: -0.0000

Data Index: 249495 (The Pile)

Max Activating Token Index: 594