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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1017. Min Range: -2.1017

Max Act: 2.1017. Min Act: -0.0000

Data Index: 1102106 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.8367. Min Act: -0.0000

Data Index: 618208 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1177012 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.9336. Min Act: -0.0000

Data Index: 1295709 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1326362 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.8178. Min Act: -0.0000

Data Index: 60284 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.7962. Min Act: -0.0000

Data Index: 180250 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.7816. Min Act: -0.0000

Data Index: 895151 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.7540. Min Act: -0.0000

Data Index: 636403 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1008814 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1066277 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.7363. Min Act: -0.0000

Data Index: 627546 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.6542. Min Act: -0.0000

Data Index: 383021 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.6793. Min Act: -0.0000

Data Index: 719280 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5334. Min Act: -0.0000

Data Index: 482571 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.7265. Min Act: -0.0000

Data Index: 911180 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5888. Min Act: -0.0000

Data Index: 723724 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5599. Min Act: -0.0000

Data Index: 12119 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5255. Min Act: -0.0000

Data Index: 67151 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 2.1017. Min Range: -2.1017

Max Act: 1.5794. Min Act: -0.0000

Data Index: 752498 (C4 (Web Text))

Max Activating Token Index: 977