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

Dataset: The Pile

Neuron 2469 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: 1.0586. Min Range: -1.0586

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1804117 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5557. Min Act: -0.0000

Data Index: 664913 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5883. Min Act: -0.0000

Data Index: 787596 (The Pile)

Max Activating Token Index: 483

Text #3

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1095032 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5442. Min Act: -0.0000

Data Index: 337551 (The Pile)

Max Activating Token Index: 196

Text #5

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5742. Min Act: -0.0000

Data Index: 983207 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5230. Min Act: -0.0000

Data Index: 585705 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1676489 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1793296 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5325. Min Act: -0.0000

Data Index: 979925 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5084. Min Act: -0.0000

Data Index: 824089 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.4721. Min Act: -0.0000

Data Index: 959316 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1674013 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5338. Min Act: -0.0000

Data Index: 1441285 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1821529 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1940092 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1840280 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1878712 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.4974. Min Act: -0.0000

Data Index: 66826 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 1.0586. Min Range: -1.0586

Max Act: 0.5174. Min Act: -0.0000

Data Index: 83603 (The Pile)

Max Activating Token Index: 902