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

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

Neuron 247 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.9812. Min Act: -0.0000

Data Index: 1015159 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.4812. Min Act: -0.0000

Data Index: 1125580 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.3699. Min Act: -0.0000

Data Index: 389387 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1049670 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.3422. Min Act: -0.0000

Data Index: 509399 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1264197 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2696. Min Act: -0.0000

Data Index: 869811 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2016. Min Act: -0.0000

Data Index: 968027 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1018364 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.0880. Min Act: -0.0000

Data Index: 161635 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2033. Min Act: -0.0000

Data Index: 400506 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.1845. Min Act: -0.0000

Data Index: 624027 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.0851. Min Act: -0.0000

Data Index: 305342 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.1490. Min Act: -0.0000

Data Index: 565312 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2132. Min Act: -0.0000

Data Index: 531237 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.1357. Min Act: -0.0000

Data Index: 148809 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.1967. Min Act: -0.0000

Data Index: 318750 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.1311. Min Act: -0.0000

Data Index: 270917 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.1175. Min Act: -0.0000

Data Index: 220661 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 1.9812. Min Range: -1.9812

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1257922 (C4 (Web Text))

Max Activating Token Index: 663