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

Dataset: The Pile

Neuron 3760 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: 1.7505. Min Range: -1.7505

Max Act: 1.5695. Min Act: -0.0000

Data Index: 821757 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1216881 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1927542 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5214. Min Act: -0.0000

Data Index: 1864555 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.6080. Min Act: -0.0000

Data Index: 285847 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5135. Min Act: -0.0000

Data Index: 955475 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1101927 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5128. Min Act: -0.0000

Data Index: 1861554 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.6108. Min Act: -0.0000

Data Index: 811822 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.6714. Min Act: -0.0000

Data Index: 221772 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1909907 (The Pile)

Max Activating Token Index: 211

Text #11

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5453. Min Act: -0.0000

Data Index: 973944 (The Pile)

Max Activating Token Index: 172

Text #12

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5496. Min Act: -0.0000

Data Index: 356014 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1014370 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5356. Min Act: -0.0000

Data Index: 636191 (The Pile)

Max Activating Token Index: 667

Text #15

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.4405. Min Act: -0.0000

Data Index: 701760 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5313. Min Act: -0.0000

Data Index: 570365 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5226. Min Act: -0.0000

Data Index: 896408 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5322. Min Act: -0.0000

Data Index: 1019986 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.5225. Min Act: -0.0000

Data Index: 1704346 (The Pile)

Max Activating Token Index: 443