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

Dataset: The Pile

Neuron 389 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1475415 (The Pile)

Max Activating Token Index: 762

Text #1

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5481. Min Act: -0.0000

Data Index: 340163 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.5057. Min Act: 0.0000

Data Index: 491561 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1824483 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4911. Min Act: -0.0000

Data Index: 398099 (The Pile)

Max Activating Token Index: 730

Text #5

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1418442 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4724. Min Act: -0.0000

Data Index: 194718 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1563730 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4537. Min Act: -0.0000

Data Index: 797870 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4550. Min Act: -0.0000

Data Index: 376763 (The Pile)

Max Activating Token Index: 787

Text #10

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4809. Min Act: -0.0000

Data Index: 536028 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4512. Min Act: -0.0000

Data Index: 460744 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1853825 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4191. Min Act: -0.0000

Data Index: 786537 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4221. Min Act: 0.0000

Data Index: 747842 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4296. Min Act: -0.0000

Data Index: 913391 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1363178 (The Pile)

Max Activating Token Index: 272

Text #17

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1641959 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4354. Min Act: 0.0000

Data Index: 1800656 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.5810. Min Range: -0.5810

Max Act: 0.4271. Min Act: 0.0000

Data Index: 1593171 (The Pile)

Max Activating Token Index: 273