Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 722 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1255408 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0901. Min Act: -0.0003

Data Index: 930030 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0831. Min Act: -0.0002

Data Index: 927973 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0887. Min Act: -0.0003

Data Index: 591236 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0865. Min Act: -0.0003

Data Index: 517237 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0810. Min Act: -0.0003

Data Index: 1337714 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0808. Min Act: -0.0002

Data Index: 851458 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1177364 (C4 (Web Text))

Max Activating Token Index: 569

Text #8

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1057614 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0820. Min Act: -0.0003

Data Index: 733058 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0774. Min Act: -0.0003

Data Index: 520613 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0796. Min Act: -0.0003

Data Index: 622393 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0756. Min Act: -0.0003

Data Index: 436676 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0754. Min Act: -0.0003

Data Index: 537905 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0790. Min Act: -0.0003

Data Index: 66042 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0784. Min Act: -0.0003

Data Index: 91788 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0700. Min Act: -0.0003

Data Index: 312409 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0736. Min Act: -0.0002

Data Index: 472195 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0759. Min Act: -0.0003

Data Index: 112268 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0901. Min Range: -0.0901

Max Act: 0.0732. Min Act: -0.0003

Data Index: 144094 (C4 (Web Text))

Max Activating Token Index: 71