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

Dataset: The Pile

Neuron 794 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: 0.7851. Min Range: -0.7851

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1149470 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7851. Min Act: -0.0000

Data Index: 483590 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6970. Min Act: -0.0000

Data Index: 765986 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1691544 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1085938 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6733. Min Act: -0.0000

Data Index: 732127 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1261564 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1989046 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1009741 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1275270 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1295291 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6401. Min Act: -0.0000

Data Index: 303932 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1891781 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6486. Min Act: -0.0000

Data Index: 45382 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1169990 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1434235 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1223663 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1390315 (The Pile)

Max Activating Token Index: 181

Text #18

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6104. Min Act: -0.0000

Data Index: 1769490 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1534331 (The Pile)

Max Activating Token Index: 56