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

Dataset: The Pile

Neuron 4790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1551840 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1816. Min Act: -0.0000

Data Index: 605752 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1608308 (The Pile)

Max Activating Token Index: 687

Text #3

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1091866 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1347065 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1472. Min Act: -0.0000

Data Index: 804640 (The Pile)

Max Activating Token Index: 480

Text #6

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1425. Min Act: -0.0000

Data Index: 964180 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1347161 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1577888 (The Pile)

Max Activating Token Index: 654

Text #9

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1522067 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1797891 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1431589 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1228. Min Act: -0.0000

Data Index: 293296 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1315640 (The Pile)

Max Activating Token Index: 862

Text #14

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1623805 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1190. Min Act: -0.0000

Data Index: 269181 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1752644 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1199255 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1796360 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1628048 (The Pile)

Max Activating Token Index: 656