Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.9751. Min Act: -0.0002

Data Index: 754532 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.9201. Min Act: -0.0002

Data Index: 352228 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.8670. Min Act: -0.0002

Data Index: 25358 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.8625. Min Act: -0.0002

Data Index: 382058 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.8465. Min Act: -0.0002

Data Index: 148966 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.8028. Min Act: -0.0002

Data Index: 1273842 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.8020. Min Act: -0.0002

Data Index: 252844 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7530. Min Act: -0.0002

Data Index: 1076048 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.8126. Min Act: -0.0002

Data Index: 1328651 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7766. Min Act: -0.0002

Data Index: 212344 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7512. Min Act: -0.0002

Data Index: 463184 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7863. Min Act: -0.0002

Data Index: 753372 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7591. Min Act: -0.0002

Data Index: 1220418 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7795. Min Act: -0.0002

Data Index: 805262 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7764. Min Act: -0.0002

Data Index: 582780 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7663. Min Act: -0.0002

Data Index: 748950 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.6822. Min Act: -0.0002

Data Index: 1310694 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7285. Min Act: -0.0002

Data Index: 402587 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.6955. Min Act: -0.0002

Data Index: 432542 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.9751. Min Range: -0.9751

Max Act: 0.7186. Min Act: -0.0002

Data Index: 677161 (C4 (Web Text))

Max Activating Token Index: 51