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

Dataset: The Pile

Neuron 5105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3479. Min Act: -0.0000

Data Index: 1861320 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1971980 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3232. Min Act: -0.0000

Data Index: 94945 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2979. Min Act: -0.0000

Data Index: 177787 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3143. Min Act: -0.0000

Data Index: 117677 (The Pile)

Max Activating Token Index: 282

Text #5

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2792. Min Act: -0.0000

Data Index: 198752 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2571. Min Act: -0.0000

Data Index: 639408 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2990. Min Act: -0.0000

Data Index: 1838551 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.3077. Min Act: -0.0000

Data Index: 164622 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2186. Min Act: -0.0000

Data Index: 1850001 (The Pile)

Max Activating Token Index: 438

Text #10

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.2503. Min Act: -0.0000

Data Index: 628156 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1455332 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0867. Min Act: -0.0000

Data Index: 339545 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0566. Min Act: -0.0000

Data Index: 845286 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9105. Min Act: -0.0000

Data Index: 301758 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9247. Min Act: -0.0001

Data Index: 657612 (The Pile)

Max Activating Token Index: 485

Text #16

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1697414 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1595010 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0659. Min Act: -0.0000

Data Index: 426073 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9876. Min Act: -0.0001

Data Index: 1603204 (The Pile)

Max Activating Token Index: 455