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

Dataset: The Pile

Neuron 642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.4471. Min Act: -0.0000

Data Index: 1075488 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.2430. Min Act: -0.0000

Data Index: 344939 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1646154 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1407906 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1267048 (The Pile)

Max Activating Token Index: 760

Text #5

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1477. Min Act: -0.0000

Data Index: 712814 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1391. Min Act: -0.0000

Data Index: 365718 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1553. Min Act: -0.0000

Data Index: 80252 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.1234. Min Act: -0.0000

Data Index: 837030 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1221000 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 1.4471. Min Range: -1.4471

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1667703 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0720. Min Act: -0.0000

Data Index: 652629 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 1.4471. Min Range: -1.4471

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1674669 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0573. Min Act: -0.0000

Data Index: 501533 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0456. Min Act: -0.0000

Data Index: 254918 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 1.4471. Min Range: -1.4471

Max Act: 0.9800. Min Act: -0.0000

Data Index: 695855 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0345. Min Act: -0.0000

Data Index: 460955 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 1.4471. Min Range: -1.4471

Max Act: 0.9996. Min Act: -0.0000

Data Index: 38948 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0116. Min Act: -0.0000

Data Index: 892666 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 1.4471. Min Range: -1.4471

Max Act: 1.0407. Min Act: -0.0000

Data Index: 724539 (The Pile)

Max Activating Token Index: 344