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

Dataset: The Pile

Neuron 2721 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: 1.9575. Min Range: -1.9575

Max Act: 1.8059. Min Act: -0.0000

Data Index: 761652 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.9575. Min Act: -0.0000

Data Index: 995197 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1159732 (The Pile)

Max Activating Token Index: 90

Text #3

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.6886. Min Act: -0.0000

Data Index: 718830 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1764999 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.6328. Min Act: -0.0000

Data Index: 321649 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1250189 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.6021. Min Act: -0.0000

Data Index: 405475 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5291. Min Act: -0.0000

Data Index: 408051 (The Pile)

Max Activating Token Index: 634

Text #9

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5599. Min Act: -0.0000

Data Index: 758116 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.4891. Min Act: -0.0000

Data Index: 776609 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.4811. Min Act: -0.0000

Data Index: 865987 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5368. Min Act: -0.0000

Data Index: 252680 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1305130 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5627. Min Act: -0.0000

Data Index: 1005527 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.5196. Min Act: -0.0000

Data Index: 91780 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.4675. Min Act: -0.0000

Data Index: 443595 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.3823. Min Act: -0.0000

Data Index: 725587 (The Pile)

Max Activating Token Index: 530

Text #18

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1518366 (The Pile)

Max Activating Token Index: 777

Text #19

Max Range: 1.9575. Min Range: -1.9575

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1639365 (The Pile)

Max Activating Token Index: 158