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

Dataset: The Pile

Neuron 3329 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4451. Min Act: -0.0000

Data Index: 1858916 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4633. Min Act: -0.0000

Data Index: 20398 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1351212 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1763617 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3991. Min Act: -0.0000

Data Index: 377226 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1412758 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4251. Min Act: -0.0000

Data Index: 184858 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4048. Min Act: -0.0000

Data Index: 218538 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.4128. Min Act: -0.0000

Data Index: 518017 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1419647 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1700185 (The Pile)

Max Activating Token Index: 977

Text #11

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3415. Min Act: -0.0000

Data Index: 381061 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1558667 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1982176 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1398415 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3657. Min Act: -0.0000

Data Index: 204118 (The Pile)

Max Activating Token Index: 280

Text #16

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1419852 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1895773 (The Pile)

Max Activating Token Index: 106

Text #18

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3598. Min Act: -0.0000

Data Index: 231787 (The Pile)

Max Activating Token Index: 783

Text #19

Max Range: 0.4633. Min Range: -0.4633

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1865365 (The Pile)

Max Activating Token Index: 484