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

Dataset: The Pile

Neuron 4283 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: 0.8470. Min Range: -0.8470

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1544084 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8470. Min Act: 0.0000

Data Index: 1300390 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1951061 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8044. Min Act: -0.0000

Data Index: 385861 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7514. Min Act: -0.0000

Data Index: 681970 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1204435 (The Pile)

Max Activating Token Index: 925

Text #6

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6947. Min Act: -0.0000

Data Index: 148481 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1093181 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6556. Min Act: -0.0000

Data Index: 172939 (The Pile)

Max Activating Token Index: 217

Text #9

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1399616 (The Pile)

Max Activating Token Index: 579

Text #10

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1818335 (The Pile)

Max Activating Token Index: 613

Text #11

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5868. Min Act: -0.0000

Data Index: 662387 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1898883 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5835. Min Act: -0.0000

Data Index: 143886 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5559. Min Act: -0.0000

Data Index: 201245 (The Pile)

Max Activating Token Index: 798

Text #15

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5770. Min Act: -0.0000

Data Index: 424628 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1496734 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1876487 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5616. Min Act: -0.0000

Data Index: 62636 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1909916 (The Pile)

Max Activating Token Index: 424