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

Dataset: The Pile

Neuron 4419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1480432 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3236. Min Act: -0.0000

Data Index: 464747 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3798. Min Act: -0.0000

Data Index: 942883 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3772. Min Act: -0.0000

Data Index: 989285 (The Pile)

Max Activating Token Index: 679

Text #4

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1248799 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2800. Min Act: -0.0000

Data Index: 770086 (The Pile)

Max Activating Token Index: 392

Text #6

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1018673 (The Pile)

Max Activating Token Index: 960

Text #7

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1867848 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2726. Min Act: -0.0000

Data Index: 129083 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1725356 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1345584 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1011782 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1424576 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2503. Min Act: -0.0000

Data Index: 816734 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2210. Min Act: -0.0000

Data Index: 653550 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2263. Min Act: -0.0000

Data Index: 865299 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2866. Min Act: -0.0000

Data Index: 1870304 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2374. Min Act: -0.0000

Data Index: 30325 (The Pile)

Max Activating Token Index: 585

Text #18

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2696. Min Act: -0.0000

Data Index: 193489 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.4697. Min Range: -0.4697

Max Act: 0.2432. Min Act: -0.0000

Data Index: 463007 (The Pile)

Max Activating Token Index: 183