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

Dataset: The Pile

Neuron 4730 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: 0.7776. Min Range: -0.7776

Max Act: 0.7776. Min Act: -0.0000

Data Index: 1226468 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5794. Min Act: -0.0000

Data Index: 687453 (The Pile)

Max Activating Token Index: 653

Text #2

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1682292 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1282277 (The Pile)

Max Activating Token Index: 566

Text #4

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6150. Min Act: -0.0000

Data Index: 90086 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1927946 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5578. Min Act: -0.0000

Data Index: 381834 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5738. Min Act: -0.0000

Data Index: 116056 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.4982. Min Act: -0.0001

Data Index: 487908 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1201585 (The Pile)

Max Activating Token Index: 23

Text #10

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1896758 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.6027. Min Act: -0.0000

Data Index: 290652 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5535. Min Act: -0.0000

Data Index: 1140240 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5542. Min Act: -0.0000

Data Index: 1566516 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1036997 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.4850. Min Act: -0.0000

Data Index: 171023 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1695983 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5281. Min Act: -0.0000

Data Index: 676647 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1965730 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.7776. Min Range: -0.7776

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1641840 (The Pile)

Max Activating Token Index: 118