Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.7544. Min Act: -0.0000

Data Index: 784298 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5995. Min Act: -0.0000

Data Index: 43405 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1587741 (The Pile)

Max Activating Token Index: 639

Text #3

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5727. Min Act: -0.0000

Data Index: 360537 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5387. Min Act: -0.0000

Data Index: 814956 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1572717 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4987. Min Act: -0.0000

Data Index: 616399 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4971. Min Act: -0.0000

Data Index: 954579 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1111243 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4947. Min Act: -0.0000

Data Index: 527748 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1050575 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4784. Min Act: -0.0000

Data Index: 805851 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.5073. Min Act: -0.0001

Data Index: 743070 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4736. Min Act: -0.0000

Data Index: 773657 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4869. Min Act: -0.0000

Data Index: 445225 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4841. Min Act: -0.0000

Data Index: 2149 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1716164 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1366443 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1762745 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 0.7544. Min Range: -0.7544

Max Act: 0.4834. Min Act: -0.0000

Data Index: 690601 (The Pile)

Max Activating Token Index: 795