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

Dataset: The Pile

Neuron 427 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: 0.7391. Min Range: -0.7391

Max Act: 0.7345. Min Act: -0.0000

Data Index: 849527 (The Pile)

Max Activating Token Index: 712

Text #1

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7230. Min Act: -0.0000

Data Index: 655246 (The Pile)

Max Activating Token Index: 441

Text #2

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7391. Min Act: -0.0000

Data Index: 107942 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6737. Min Act: -0.0000

Data Index: 801526 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7275. Min Act: -0.0000

Data Index: 563519 (The Pile)

Max Activating Token Index: 471

Text #5

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1049637 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7287. Min Act: -0.0000

Data Index: 721705 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6795. Min Act: -0.0000

Data Index: 980848 (The Pile)

Max Activating Token Index: 476

Text #8

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1155601 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6901. Min Act: -0.0000

Data Index: 1625970 (The Pile)

Max Activating Token Index: 622

Text #10

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6861. Min Act: -0.0000

Data Index: 141026 (The Pile)

Max Activating Token Index: 415

Text #11

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1536337 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7086. Min Act: -0.0000

Data Index: 160123 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6874. Min Act: -0.0000

Data Index: 990763 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7054. Min Act: -0.0000

Data Index: 1287807 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6250. Min Act: -0.0000

Data Index: 562543 (The Pile)

Max Activating Token Index: 605

Text #16

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1287383 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1996702 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1564506 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1016695 (The Pile)

Max Activating Token Index: 551