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

Dataset: The Pile

Neuron 2583 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7031. Min Range: -3.7031

Max Act: 3.7031. Min Act: -0.0000

Data Index: 1036957 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.6011. Min Act: -0.0000

Data Index: 289960 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.3702. Min Act: -0.0000

Data Index: 1269104 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.4732. Min Act: -0.0000

Data Index: 631545 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.4461. Min Act: -0.0000

Data Index: 304725 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.3937. Min Act: -0.0000

Data Index: 329645 (The Pile)

Max Activating Token Index: 192

Text #6

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.4782. Min Act: -0.0000

Data Index: 456455 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.4740. Min Act: -0.0000

Data Index: 722267 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.4368. Min Act: -0.0000

Data Index: 143477 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.2000. Min Act: -0.0000

Data Index: 1326120 (The Pile)

Max Activating Token Index: 404

Text #10

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.2713. Min Act: -0.0000

Data Index: 827013 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.2261. Min Act: -0.0000

Data Index: 1003928 (The Pile)

Max Activating Token Index: 744

Text #12

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.2177. Min Act: -0.0000

Data Index: 689059 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1741725 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.0627. Min Act: -0.0000

Data Index: 1907051 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.1576. Min Act: -0.0000

Data Index: 283437 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.2390. Min Act: -0.0000

Data Index: 173025 (The Pile)

Max Activating Token Index: 323

Text #17

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.0098. Min Act: -0.0000

Data Index: 135306 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.2435. Min Act: -0.0000

Data Index: 1245110 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 3.7031. Min Range: -3.7031

Max Act: 2.0920. Min Act: -0.0000

Data Index: 1366443 (The Pile)

Max Activating Token Index: 25