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

Dataset: The Pile

Neuron 4357 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: 1.0028. Min Range: -1.0028

Max Act: 1.0028. Min Act: -0.0000

Data Index: 289396 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1622940 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1877556 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8809. Min Act: -0.0000

Data Index: 747477 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.9060. Min Act: -0.0000

Data Index: 368390 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8580. Min Act: -0.0000

Data Index: 983752 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7942. Min Act: -0.0000

Data Index: 530587 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8496. Min Act: -0.0000

Data Index: 393927 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1689594 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1029639 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1845848 (The Pile)

Max Activating Token Index: 801

Text #11

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1829154 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1163711 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7718. Min Act: -0.0000

Data Index: 751449 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7794. Min Act: -0.0000

Data Index: 798509 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1137872 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7535. Min Act: -0.0000

Data Index: 284830 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1025922 (The Pile)

Max Activating Token Index: 272

Text #18

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.7160. Min Act: 0.0000

Data Index: 1921663 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 1.0028. Min Range: -1.0028

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1280782 (The Pile)

Max Activating Token Index: 692