Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1660374 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.6017. Min Act: -0.0000

Data Index: 640150 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5487. Min Act: -0.0000

Data Index: 788205 (The Pile)

Max Activating Token Index: 964

Text #3

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1825226 (The Pile)

Max Activating Token Index: 444

Text #4

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5381. Min Act: -0.0000

Data Index: 358561 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5161. Min Act: -0.0000

Data Index: 600719 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4799. Min Act: -0.0000

Data Index: 414819 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.5094. Min Act: -0.0000

Data Index: 412847 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1182713 (The Pile)

Max Activating Token Index: 699

Text #9

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1771810 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4843. Min Act: -0.0000

Data Index: 988617 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1552184 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4614. Min Act: -0.0000

Data Index: 742987 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1757415 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4821. Min Act: -0.0000

Data Index: 770762 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1584112 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4675. Min Act: -0.0000

Data Index: 236175 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4390. Min Act: -0.0000

Data Index: 363619 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4695. Min Act: -0.0000

Data Index: 938630 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.6017. Min Range: -0.6017

Max Act: 0.4546. Min Act: 0.0000

Data Index: 635004 (The Pile)

Max Activating Token Index: 14