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

Dataset: The Pile

Neuron 3056 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5146. Min Range: -3.5146

Max Act: 3.5146. Min Act: -0.0000

Data Index: 25372 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 3.5146. Min Range: -3.5146

Max Act: 3.2217. Min Act: -0.0000

Data Index: 1374727 (The Pile)

Max Activating Token Index: 935

Text #2

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.9420. Min Act: -0.0000

Data Index: 1238718 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.9755. Min Act: -0.0000

Data Index: 1808324 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.9549. Min Act: -0.0000

Data Index: 446173 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.9665. Min Act: -0.0000

Data Index: 180717 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.8047. Min Act: -0.0000

Data Index: 594272 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.7653. Min Act: -0.0000

Data Index: 1940641 (The Pile)

Max Activating Token Index: 191

Text #8

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.6515. Min Act: -0.0000

Data Index: 653030 (The Pile)

Max Activating Token Index: 203

Text #9

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.9316. Min Act: -0.0000

Data Index: 407288 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.4524. Min Act: -0.0000

Data Index: 459086 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.5720. Min Act: -0.0000

Data Index: 941242 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.7189. Min Act: -0.0000

Data Index: 170953 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.3737. Min Act: -0.0000

Data Index: 1463420 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.3589. Min Act: -0.0000

Data Index: 1388098 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.2214. Min Act: -0.0000

Data Index: 3456 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.2217. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 3.5146. Min Range: -3.5146

Max Act: 1.9927. Min Act: -0.0000

Data Index: 639644 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.1762. Min Act: -0.0000

Data Index: 960341 (The Pile)

Max Activating Token Index: 294

Text #19

Max Range: 3.5146. Min Range: -3.5146

Max Act: 2.1776. Min Act: -0.0000

Data Index: 873459 (The Pile)

Max Activating Token Index: 597