Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3444 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0787. Min Act: -0.0000

Data Index: 467179 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0810. Min Act: -0.0001

Data Index: 865013 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0769. Min Act: -0.0001

Data Index: 455857 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0762. Min Act: -0.0000

Data Index: 145724 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0794. Min Act: -0.0000

Data Index: 112887 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0789. Min Act: -0.0001

Data Index: 83363 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0757. Min Act: -0.0001

Data Index: 438737 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0743. Min Act: -0.0000

Data Index: 607791 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0001

Data Index: 706553 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1318333 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0746. Min Act: -0.0001

Data Index: 818620 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1016183 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0744. Min Act: -0.0000

Data Index: 823067 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1320054 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0683. Min Act: -0.0001

Data Index: 498972 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0700. Min Act: -0.0001

Data Index: 450466 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0784. Min Act: -0.0001

Data Index: 166847 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1104409 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0716. Min Act: -0.0001

Data Index: 9221 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0712. Min Act: -0.0000

Data Index: 873284 (C4 (Web Text))

Max Activating Token Index: 766