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

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

Neuron 1738 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0617. Min Act: -0.0006

Data Index: 1205272 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0544. Min Act: -0.0006

Data Index: 1201836 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0514. Min Act: -0.0006

Data Index: 1059738 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0500. Min Act: -0.0006

Data Index: 323281 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0495. Min Act: -0.0006

Data Index: 1007716 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0486. Min Act: -0.0006

Data Index: 976395 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0485. Min Act: -0.0006

Data Index: 381756 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0503. Min Act: -0.0006

Data Index: 933658 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0481. Min Act: -0.0006

Data Index: 889815 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0480. Min Act: -0.0006

Data Index: 30841 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0480. Min Act: -0.0005

Data Index: 400602 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0484. Min Act: -0.0006

Data Index: 507198 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0493. Min Act: -0.0006

Data Index: 1223290 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0508. Min Act: -0.0006

Data Index: 1268326 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0476. Min Act: -0.0006

Data Index: 459675 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0467. Min Act: -0.0005

Data Index: 583346 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0473. Min Act: -0.0006

Data Index: 835624 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0491. Min Act: -0.0006

Data Index: 1176021 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0479. Min Act: -0.0006

Data Index: 321424 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.0617. Min Range: -0.0617

Max Act: 0.0481. Min Act: -0.0006

Data Index: 835461 (C4 (Web Text))

Max Activating Token Index: 859