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

Dataset: The Pile

Neuron 4762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 12.7067. Min Range: -12.7067

Max Act: 12.7067. Min Act: -0.0000

Data Index: 727540 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 12.7067. Min Range: -12.7067

Max Act: 12.1758. Min Act: -0.0000

Data Index: 403806 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.9179. Min Act: -0.0000

Data Index: 287026 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 12.7067. Min Range: -12.7067

Max Act: 12.0111. Min Act: -0.0000

Data Index: 1147184 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.8874. Min Act: -0.0000

Data Index: 1733535 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 12.7067. Min Range: -12.7067

Max Act: 12.0857. Min Act: -0.0000

Data Index: 912895 (The Pile)

Max Activating Token Index: 709

Text #6

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.9807. Min Act: -0.0000

Data Index: 1932106 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.8237. Min Act: -0.0000

Data Index: 1929070 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.8068. Min Act: -0.0000

Data Index: 1236201 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.7995. Min Act: -0.0000

Data Index: 385799 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.7798. Min Act: -0.0000

Data Index: 441245 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.8550. Min Act: -0.0000

Data Index: 588839 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.5487. Min Act: -0.0000

Data Index: 981294 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.5238. Min Act: -0.0000

Data Index: 275454 (The Pile)

Max Activating Token Index: 201

Text #14

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.9147. Min Act: -0.0000

Data Index: 990994 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.8010. Min Act: -0.0000

Data Index: 1206858 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.7977. Min Act: -0.0000

Data Index: 52389 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.6863. Min Act: -0.0000

Data Index: 479336 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.7717. Min Act: -0.0000

Data Index: 1735480 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 12.7067. Min Range: -12.7067

Max Act: 11.5502. Min Act: -0.0000

Data Index: 1767750 (The Pile)

Max Activating Token Index: 253