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

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

Neuron 2898 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1693. Min Act: -0.0001

Data Index: 569478 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0586. Min Act: -0.0001

Data Index: 518157 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.1016. Min Act: -0.0001

Data Index: 1001433 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.1693. Min Range: -1.1693

Max Act: 1.0535. Min Act: -0.0001

Data Index: 811111 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9563. Min Act: -0.0001

Data Index: 1081683 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9924. Min Act: -0.0001

Data Index: 961527 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1169563 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9282. Min Act: -0.0001

Data Index: 584330 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9325. Min Act: -0.0001

Data Index: 1017695 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.9001. Min Act: -0.0001

Data Index: 735974 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8917. Min Act: -0.0001

Data Index: 982671 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8323. Min Act: -0.0001

Data Index: 109964 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8830. Min Act: -0.0001

Data Index: 1187729 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8743. Min Act: -0.0001

Data Index: 59273 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8934. Min Act: -0.0001

Data Index: 724653 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8801. Min Act: -0.0001

Data Index: 691392 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8181. Min Act: -0.0001

Data Index: 504095 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8719. Min Act: -0.0001

Data Index: 265475 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8227. Min Act: -0.0001

Data Index: 249576 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.1693. Min Range: -1.1693

Max Act: 0.8401. Min Act: -0.0001

Data Index: 445530 (C4 (Web Text))

Max Activating Token Index: 413