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

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

Neuron 2447 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0003

Data Index: 182684 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0581. Min Act: -0.0003

Data Index: 437151 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0566. Min Act: -0.0002

Data Index: 172215 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0549. Min Act: -0.0003

Data Index: 939776 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1181555 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0550. Min Act: -0.0003

Data Index: 687601 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1645253 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0511. Min Act: -0.0003

Data Index: 920587 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0489. Min Act: -0.0003

Data Index: 867923 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0497. Min Act: -0.0003

Data Index: 509990 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0485. Min Act: -0.0002

Data Index: 541960 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0508. Min Act: -0.0003

Data Index: 703482 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0509. Min Act: -0.0002

Data Index: 404995 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0517. Min Act: -0.0003

Data Index: 6760 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0481. Min Act: -0.0003

Data Index: 543220 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0473. Min Act: -0.0003

Data Index: 72399 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0467. Min Act: -0.0003

Data Index: 501805 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0490. Min Act: -0.0003

Data Index: 945479 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0488. Min Act: -0.0003

Data Index: 290644 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0496. Min Act: -0.0002

Data Index: 498806 (C4 (Web Text))

Max Activating Token Index: 390