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

Dataset: The Pile

Neuron 2730 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: 0.8090. Min Range: -0.8090

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1294563 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1306027 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6850. Min Act: -0.0000

Data Index: 557027 (The Pile)

Max Activating Token Index: 122

Text #3

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6511. Min Act: -0.0000

Data Index: 343684 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1736603 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6416. Min Act: -0.0000

Data Index: 870801 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1587902 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1115425 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6011. Min Act: -0.0000

Data Index: 1059629 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1766393 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1029121 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1290299 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1599720 (The Pile)

Max Activating Token Index: 493

Text #13

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5765. Min Act: 0.0000

Data Index: 1110936 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5950. Min Act: -0.0000

Data Index: 357745 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5699. Min Act: -0.0000

Data Index: 973211 (The Pile)

Max Activating Token Index: 508

Text #16

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1453974 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1675934 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5821. Min Act: -0.0000

Data Index: 62924 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1794549 (The Pile)

Max Activating Token Index: 284