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

Dataset: The Pile

Neuron 1627 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1470274 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0849. Min Act: -0.0000

Data Index: 609228 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0224. Min Act: -0.0000

Data Index: 772477 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9711. Min Act: -0.0000

Data Index: 1372977 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1021973 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1367743 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9889. Min Act: -0.0000

Data Index: 598612 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9881. Min Act: -0.0000

Data Index: 172922 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1723994 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9486. Min Act: -0.0000

Data Index: 796846 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1381229 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1308205 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9123. Min Act: -0.0000

Data Index: 1653509 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1919843 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1556926 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9960. Min Act: -0.0000

Data Index: 617797 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 1.1211. Min Range: -1.1211

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1786361 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9659. Min Act: -0.0000

Data Index: 816779 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1691345 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.1211. Min Range: -1.1211

Max Act: 0.9331. Min Act: -0.0000

Data Index: 527625 (The Pile)

Max Activating Token Index: 541