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

Dataset: The Pile

Neuron 286 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: 0.1860. Min Range: -0.1860

Max Act: 0.1860. Min Act: -0.0000

Data Index: 37502 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1745199 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1460252 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1704973 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1592. Min Act: -0.0000

Data Index: 204806 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1706. Min Act: -0.0000

Data Index: 484075 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1535. Min Act: -0.0000

Data Index: 1352009 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1563. Min Act: -0.0000

Data Index: 873320 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1490. Min Act: -0.0000

Data Index: 1212221 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1850702 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1917062 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1496. Min Act: -0.0000

Data Index: 76512 (The Pile)

Max Activating Token Index: 953

Text #12

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1467. Min Act: -0.0000

Data Index: 18101 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1430. Min Act: -0.0000

Data Index: 467664 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1398. Min Act: -0.0000

Data Index: 658434 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1179770 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1593264 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1214588 (The Pile)

Max Activating Token Index: 571

Text #18

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1327. Min Act: -0.0000

Data Index: 924986 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1413. Min Act: -0.0000

Data Index: 962911 (The Pile)

Max Activating Token Index: 448