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

Dataset: The Pile

Neuron 3096 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: 0.6084. Min Range: -0.6084

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1780161 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5911. Min Act: -0.0000

Data Index: 726666 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5673. Min Act: -0.0000

Data Index: 194324 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1150642 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1005078 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5205. Min Act: -0.0000

Data Index: 730583 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1636654 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1876953 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1887254 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5023. Min Act: -0.0000

Data Index: 279594 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1958801 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1137177 (The Pile)

Max Activating Token Index: 379

Text #12

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4876. Min Act: -0.0000

Data Index: 727976 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4990. Min Act: -0.0000

Data Index: 292805 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1514664 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.5034. Min Act: -0.0000

Data Index: 158358 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4715. Min Act: -0.0000

Data Index: 801929 (The Pile)

Max Activating Token Index: 449

Text #17

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4784. Min Act: -0.0000

Data Index: 210575 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1416236 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.6084. Min Range: -0.6084

Max Act: 0.4847. Min Act: -0.0000

Data Index: 578311 (The Pile)

Max Activating Token Index: 787