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

Dataset: The Pile

Neuron 4930 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: 3.9816. Min Range: -3.9816

Max Act: 3.9536. Min Act: -0.0000

Data Index: 1724902 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.9816. Min Act: -0.0000

Data Index: 435843 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.6784. Min Act: -0.0000

Data Index: 1999158 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.3795. Min Act: -0.0000

Data Index: 1368812 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.3277. Min Act: -0.0000

Data Index: 1776472 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.5475. Min Act: -0.0000

Data Index: 552485 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.9668. Min Act: -0.0000

Data Index: 487387 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.2406. Min Act: -0.0000

Data Index: 1895997 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.3325. Min Act: -0.0000

Data Index: 676875 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 3.9816. Min Range: -3.9816

Max Act: 3.0692. Min Act: -0.0000

Data Index: 1464859 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.7489. Min Act: -0.0000

Data Index: 1864021 (The Pile)

Max Activating Token Index: 78

Text #11

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.8601. Min Act: -0.0000

Data Index: 560080 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.9921. Min Act: -0.0000

Data Index: 1632521 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.7979. Min Act: -0.0000

Data Index: 323718 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.7725. Min Act: -0.0000

Data Index: 394188 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.3366. Min Act: -0.0000

Data Index: 563707 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.5598. Min Act: -0.0000

Data Index: 375545 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.4396. Min Act: -0.0000

Data Index: 736309 (The Pile)

Max Activating Token Index: 936

Text #18

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.7433. Min Act: -0.0000

Data Index: 65380 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 3.9816. Min Range: -3.9816

Max Act: 2.5831. Min Act: -0.0000

Data Index: 169777 (The Pile)

Max Activating Token Index: 316