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

Dataset: The Pile

Neuron 1224 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: 1.2773. Min Range: -1.2773

Max Act: 1.2773. Min Act: -0.0000

Data Index: 913704 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.2288. Min Act: -0.0000

Data Index: 462661 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1688. Min Act: -0.0000

Data Index: 399965 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1609645 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1514732 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1264172 (The Pile)

Max Activating Token Index: 846

Text #6

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.1365. Min Act: -0.0000

Data Index: 586357 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1561395 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1765664 (The Pile)

Max Activating Token Index: 366

Text #9

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1147646 (The Pile)

Max Activating Token Index: 187

Text #10

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0627. Min Act: -0.0000

Data Index: 470353 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0966. Min Act: -0.0000

Data Index: 319031 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0284. Min Act: -0.0000

Data Index: 1268892 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1655973 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1188529 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0566. Min Act: -0.0000

Data Index: 635247 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1416571 (The Pile)

Max Activating Token Index: 712

Text #17

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1931751 (The Pile)

Max Activating Token Index: 543

Text #18

Max Range: 1.2773. Min Range: -1.2773

Max Act: 1.0113. Min Act: -0.0000

Data Index: 671335 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 1.2773. Min Range: -1.2773

Max Act: 0.9899. Min Act: -0.0000

Data Index: 83217 (The Pile)

Max Activating Token Index: 733