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

Dataset: The Pile

Neuron 4474 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0007. Min Act: -0.0000

Data Index: 625022 (The Pile)

Max Activating Token Index: 928

Text #1

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0000

Data Index: 174953 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0000

Data Index: 840761 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0024. Min Act: -0.0000

Data Index: 1334476 (The Pile)

Max Activating Token Index: 356

Text #4

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0008. Min Act: -0.0000

Data Index: 599833 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0000

Data Index: 1214389 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0022. Min Act: -0.0000

Data Index: 513378 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0015. Min Act: -0.0000

Data Index: 4953 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1072982 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0018. Min Act: -0.0000

Data Index: 355034 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0018. Min Act: -0.0000

Data Index: 624547 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0009. Min Act: -0.0000

Data Index: 1216689 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0010. Min Act: -0.0000

Data Index: 855274 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0000

Data Index: 865450 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0017. Min Act: -0.0000

Data Index: 2106 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1359058 (The Pile)

Max Activating Token Index: 590

Text #16

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0013. Min Act: -0.0000

Data Index: 217776 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0016. Min Act: -0.0000

Data Index: 1304129 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0015. Min Act: -0.0000

Data Index: 896751 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 0.0024. Min Range: -0.0024

Max Act: 0.0016. Min Act: -0.0000

Data Index: 1435121 (The Pile)

Max Activating Token Index: 215