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

Dataset: The Pile

Neuron 5010 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.8613. Min Act: -0.0000

Data Index: 1097341 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.7853. Min Act: -0.0000

Data Index: 697053 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.7865. Min Act: -0.0000

Data Index: 1942553 (The Pile)

Max Activating Token Index: 775

Text #3

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.6836. Min Act: -0.0000

Data Index: 278024 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1569442 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.5249. Min Act: -0.0000

Data Index: 788638 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.7025. Min Act: -0.0000

Data Index: 1439671 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1630121 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.6652. Min Act: -0.0000

Data Index: 181210 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.6615. Min Act: -0.0000

Data Index: 912645 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.5036. Min Act: -0.0000

Data Index: 1519490 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.5830. Min Act: -0.0000

Data Index: 1918062 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.7773. Min Act: -0.0000

Data Index: 20111 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.4968. Min Act: -0.0000

Data Index: 242814 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1801007 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1257671 (The Pile)

Max Activating Token Index: 340

Text #16

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.4545. Min Act: -0.0000

Data Index: 743304 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.4173. Min Act: -0.0000

Data Index: 717941 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1367398 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 1.8613. Min Range: -1.8613

Max Act: 1.4808. Min Act: -0.0000

Data Index: 856359 (The Pile)

Max Activating Token Index: 582