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

Dataset: The Pile

Neuron 771 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.2998. Min Act: -0.0000

Data Index: 1463509 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.1158. Min Act: -0.0000

Data Index: 521950 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.9808. Min Act: -0.0000

Data Index: 1741423 (The Pile)

Max Activating Token Index: 728

Text #3

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.0265. Min Act: -0.0000

Data Index: 1204549 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.7352. Min Act: -0.0000

Data Index: 433169 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.0064. Min Act: -0.0000

Data Index: 355561 (The Pile)

Max Activating Token Index: 790

Text #6

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.6821. Min Act: -0.0000

Data Index: 567377 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.0890. Min Act: -0.0000

Data Index: 1679477 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.8444. Min Act: -0.0000

Data Index: 1992272 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.9044. Min Act: -0.0000

Data Index: 1179017 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.8614. Min Act: -0.0000

Data Index: 923020 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.0902. Min Act: -0.0000

Data Index: 1962974 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.9725. Min Act: -0.0000

Data Index: 517178 (The Pile)

Max Activating Token Index: 518

Text #13

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.8126. Min Act: -0.0000

Data Index: 283343 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.8078. Min Act: -0.0000

Data Index: 1090651 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.6338. Min Act: -0.0000

Data Index: 453210 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.7620. Min Act: -0.0000

Data Index: 669068 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.7900. Min Act: -0.0000

Data Index: 824816 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 3.2998. Min Range: -3.2998

Max Act: 2.7990. Min Act: -0.0000

Data Index: 721292 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 3.2998. Min Range: -3.2998

Max Act: 3.2125. Min Act: -0.0000

Data Index: 282863 (The Pile)

Max Activating Token Index: 795