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

Dataset: The Pile

Neuron 202 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: 0.1845. Min Range: -0.1845

Max Act: 0.1845. Min Act: -0.0000

Data Index: 25563 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1798. Min Act: -0.0000

Data Index: 963645 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1264953 (The Pile)

Max Activating Token Index: 631

Text #3

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1869519 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1257323 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1460570 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1647. Min Act: -0.0000

Data Index: 59917 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1776661 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1486. Min Act: -0.0000

Data Index: 664978 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1582715 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1703. Min Act: -0.0000

Data Index: 322827 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1554364 (The Pile)

Max Activating Token Index: 422

Text #12

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1588. Min Act: -0.0000

Data Index: 88430 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1809017 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1028497 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1503355 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1086725 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1364. Min Act: -0.0000

Data Index: 152459 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1507. Min Act: -0.0000

Data Index: 304077 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 0.1845. Min Range: -0.1845

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1559049 (The Pile)

Max Activating Token Index: 786