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

Dataset: The Pile

Neuron 2830 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: 1.5842. Min Range: -1.5842

Max Act: 1.2777. Min Act: -0.0000

Data Index: 82036 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1719584 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1160941 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3979. Min Act: -0.0000

Data Index: 295924 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1497132 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4241. Min Act: -0.0000

Data Index: 1896555 (The Pile)

Max Activating Token Index: 228

Text #6

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4173. Min Act: -0.0000

Data Index: 822625 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3619. Min Act: -0.0000

Data Index: 780840 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4031. Min Act: -0.0000

Data Index: 279702 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1182710 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4201. Min Act: -0.0000

Data Index: 438751 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.4577. Min Act: -0.0000

Data Index: 344356 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3571. Min Act: -0.0000

Data Index: 305918 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3688. Min Act: -0.0000

Data Index: 907143 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3392. Min Act: -0.0000

Data Index: 585477 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3068. Min Act: -0.0000

Data Index: 270104 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3357. Min Act: -0.0000

Data Index: 1614492 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3635. Min Act: -0.0000

Data Index: 1747828 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.3156. Min Act: -0.0000

Data Index: 546842 (The Pile)

Max Activating Token Index: 384

Text #19

Max Range: 1.5842. Min Range: -1.5842

Max Act: 1.2636. Min Act: -0.0000

Data Index: 510926 (The Pile)

Max Activating Token Index: 700