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

Dataset: The Pile

Neuron 413 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.6797. Min Act: -0.0000

Data Index: 1579277 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.5325. Min Act: -0.0000

Data Index: 780590 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.4698. Min Act: -0.0000

Data Index: 522033 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.4760. Min Act: -0.0000

Data Index: 980266 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.9929. Min Act: -0.0000

Data Index: 439965 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.3039. Min Act: -0.0000

Data Index: 255712 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.3002. Min Act: -0.0000

Data Index: 453667 (The Pile)

Max Activating Token Index: 476

Text #7

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.2342. Min Act: -0.0000

Data Index: 910846 (The Pile)

Max Activating Token Index: 446

Text #8

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.1602. Min Act: -0.0000

Data Index: 1290454 (The Pile)

Max Activating Token Index: 304

Text #9

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.0526. Min Act: -0.0000

Data Index: 792581 (The Pile)

Max Activating Token Index: 715

Text #10

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.8768. Min Act: -0.0000

Data Index: 1037874 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.1796. Min Act: -0.0000

Data Index: 1697013 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 5.6797. Min Range: -5.6797

Max Act: 5.1669. Min Act: -0.0000

Data Index: 345375 (The Pile)

Max Activating Token Index: 862

Text #13

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.8898. Min Act: -0.0000

Data Index: 474806 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.7476. Min Act: -0.0000

Data Index: 303685 (The Pile)

Max Activating Token Index: 296

Text #15

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.7213. Min Act: -0.0000

Data Index: 72479 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.8858. Min Act: -0.0000

Data Index: 287050 (The Pile)

Max Activating Token Index: 627

Text #17

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.8503. Min Act: -0.0000

Data Index: 958831 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.6541. Min Act: -0.0000

Data Index: 1754573 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 5.6797. Min Range: -5.6797

Max Act: 4.9655. Min Act: -0.0000

Data Index: 179293 (The Pile)

Max Activating Token Index: 573