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

Dataset: The Pile

Neuron 2776 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: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1738938 (The Pile)

Max Activating Token Index: 998

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1522. Min Act: -0.0000

Data Index: 479703 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1656944 (The Pile)

Max Activating Token Index: 925

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1321550 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1477. Min Act: -0.0000

Data Index: 1945100 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1460. Min Act: -0.0000

Data Index: 606742 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1149730 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1433. Min Act: -0.0000

Data Index: 93799 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1456. Min Act: -0.0000

Data Index: 821123 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1406. Min Act: -0.0000

Data Index: 531831 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1507935 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1332. Min Act: -0.0000

Data Index: 101468 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1870312 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1206618 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1280727 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1024545 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1357. Min Act: -0.0000

Data Index: 568074 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1302. Min Act: -0.0000

Data Index: 34886 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1174623 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1274222 (The Pile)

Max Activating Token Index: 352