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

Dataset: The Pile

Neuron 3142 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: 0.6581. Min Range: -0.6581

Max Act: 0.6581. Min Act: 0.0000

Data Index: 643854 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1029858 (The Pile)

Max Activating Token Index: 484

Text #2

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1662023 (The Pile)

Max Activating Token Index: 765

Text #3

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5733. Min Act: -0.0000

Data Index: 814558 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5654. Min Act: -0.0000

Data Index: 883417 (The Pile)

Max Activating Token Index: 372

Text #5

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5628. Min Act: -0.0000

Data Index: 858727 (The Pile)

Max Activating Token Index: 166

Text #6

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5213. Min Act: -0.0000

Data Index: 1902615 (The Pile)

Max Activating Token Index: 955

Text #7

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5132. Min Act: -0.0000

Data Index: 367538 (The Pile)

Max Activating Token Index: 391

Text #8

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5108. Min Act: -0.0000

Data Index: 630509 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5049. Min Act: -0.0000

Data Index: 480440 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4687. Min Act: -0.0000

Data Index: 754392 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1673624 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4725. Min Act: -0.0000

Data Index: 215915 (The Pile)

Max Activating Token Index: 371

Text #13

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4465. Min Act: 0.0000

Data Index: 1826903 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4876. Min Act: -0.0000

Data Index: 184538 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1483903 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4786. Min Act: 0.0000

Data Index: 92594 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4458. Min Act: -0.0000

Data Index: 752059 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1250160 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.6581. Min Range: -0.6581

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1675784 (The Pile)

Max Activating Token Index: 67