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

Dataset: The Pile

Neuron 2869 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: 1.3977. Min Range: -1.3977

Max Act: 1.3977. Min Act: -0.0000

Data Index: 723892 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1518966 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.2713. Min Act: -0.0000

Data Index: 627769 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1057771 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1463550 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0563. Min Act: -0.0000

Data Index: 944199 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1564968 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0348. Min Act: -0.0000

Data Index: 41572 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1395349 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0738. Min Act: -0.0000

Data Index: 562464 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0576. Min Act: -0.0000

Data Index: 1677214 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0464. Min Act: -0.0000

Data Index: 1279307 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9306. Min Act: -0.0000

Data Index: 111621 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9886. Min Act: -0.0000

Data Index: 121187 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1150099 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9081. Min Act: -0.0000

Data Index: 669501 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1238297 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 1.3977. Min Range: -1.3977

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1879184 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9126. Min Act: -0.0000

Data Index: 199470 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 1.3977. Min Range: -1.3977

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1848947 (The Pile)

Max Activating Token Index: 465