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

Dataset: The Pile

Neuron 4743 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.5262. Min Act: -0.0000

Data Index: 528041 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.6235. Min Act: -0.0000

Data Index: 381218 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.4292. Min Act: -0.0000

Data Index: 709867 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1833. Min Act: -0.0000

Data Index: 901292 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3911. Min Act: -0.0000

Data Index: 403782 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3257. Min Act: -0.0000

Data Index: 641398 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1559579 (The Pile)

Max Activating Token Index: 634

Text #7

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2825. Min Act: -0.0000

Data Index: 168395 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2074. Min Act: -0.0000

Data Index: 840945 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1823. Min Act: -0.0000

Data Index: 224675 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1681. Min Act: -0.0000

Data Index: 828476 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.3150. Min Act: -0.0000

Data Index: 60669 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1501840 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1076300 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1210966 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2877. Min Act: -0.0000

Data Index: 692435 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2047. Min Act: -0.0000

Data Index: 484261 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.2794. Min Act: -0.0000

Data Index: 1268526 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1522805 (The Pile)

Max Activating Token Index: 657

Text #19

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1909. Min Act: -0.0000

Data Index: 153561 (The Pile)

Max Activating Token Index: 605