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

Dataset: The Pile

Neuron 3772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.8242. Min Act: -0.0000

Data Index: 39745 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1970305 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.8242. Min Range: -1.8242

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1142487 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.2037. Min Act: -0.0000

Data Index: 1395580 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.2461. Min Act: -0.0000

Data Index: 938684 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.1259. Min Act: -0.0000

Data Index: 1454738 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.0478. Min Act: -0.0000

Data Index: 1845268 (The Pile)

Max Activating Token Index: 415

Text #7

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1347702 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1367379 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.1222. Min Act: -0.0000

Data Index: 1651250 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.0521. Min Act: -0.0000

Data Index: 819839 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 1.8242. Min Range: -1.8242

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1794203 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.0448. Min Act: -0.0000

Data Index: 553398 (The Pile)

Max Activating Token Index: 658

Text #13

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.0318. Min Act: -0.0000

Data Index: 248275 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.1278. Min Act: -0.0000

Data Index: 716571 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 1.8242. Min Range: -1.8242

Max Act: 0.9948. Min Act: -0.0000

Data Index: 1447024 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.0896. Min Act: -0.0000

Data Index: 870226 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 1.8242. Min Range: -1.8242

Max Act: 1.0702. Min Act: -0.0000

Data Index: 1745331 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 1.8242. Min Range: -1.8242

Max Act: 0.9578. Min Act: -0.0000

Data Index: 391059 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.8242. Min Range: -1.8242

Max Act: 0.8710. Min Act: -0.0000

Data Index: 1873072 (The Pile)

Max Activating Token Index: 797