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

Dataset: The Pile

Neuron 4086 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: 0.4614. Min Range: -0.4614

Max Act: 0.4606. Min Act: -0.0000

Data Index: 405986 (The Pile)

Max Activating Token Index: 875

Text #1

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.4614. Min Act: -0.0000

Data Index: 493100 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3843. Min Act: -0.0000

Data Index: 144387 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3575. Min Act: -0.0000

Data Index: 553079 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3419. Min Act: -0.0000

Data Index: 849147 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3108. Min Act: -0.0000

Data Index: 774439 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3170. Min Act: -0.0000

Data Index: 221086 (The Pile)

Max Activating Token Index: 896

Text #7

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3178. Min Act: -0.0000

Data Index: 355553 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1544097 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3023. Min Act: -0.0000

Data Index: 609408 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1434040 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1086680 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2841. Min Act: -0.0000

Data Index: 214325 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2994. Min Act: -0.0000

Data Index: 452644 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1152725 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2754. Min Act: -0.0000

Data Index: 82725 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2745. Min Act: -0.0000

Data Index: 893204 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2740. Min Act: -0.0000

Data Index: 1229273 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1069221 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1638260 (The Pile)

Max Activating Token Index: 416