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

Dataset: The Pile

Neuron 4391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.4827. Min Act: -0.0000

Data Index: 426056 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.4657. Min Act: -0.0000

Data Index: 113638 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.0831. Min Act: -0.0000

Data Index: 548771 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.0135. Min Act: -0.0000

Data Index: 761771 (The Pile)

Max Activating Token Index: 343

Text #4

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.0557. Min Act: -0.0000

Data Index: 482155 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 1.4827. Min Range: -1.4827

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1243920 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1646878 (The Pile)

Max Activating Token Index: 461

Text #7

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9859. Min Act: -0.0000

Data Index: 459375 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9623. Min Act: -0.0000

Data Index: 889972 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9485. Min Act: -0.0000

Data Index: 684900 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9319. Min Act: -0.0000

Data Index: 895467 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9228. Min Act: -0.0000

Data Index: 1626179 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9421. Min Act: -0.0000

Data Index: 459190 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.9097. Min Act: -0.0000

Data Index: 1716361 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.8852. Min Act: -0.0000

Data Index: 707764 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1839541 (The Pile)

Max Activating Token Index: 960

Text #16

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1782374 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1380234 (The Pile)

Max Activating Token Index: 529

Text #18

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.8281. Min Act: -0.0000

Data Index: 452352 (The Pile)

Max Activating Token Index: 970

Text #19

Max Range: 1.4827. Min Range: -1.4827

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1276517 (The Pile)

Max Activating Token Index: 894