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

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

Neuron 422 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: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 719844 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0635. Min Act: -0.0003

Data Index: 127046 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0539. Min Act: -0.0003

Data Index: 292470 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1036155 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0510. Min Act: -0.0003

Data Index: 554091 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1122452 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0517. Min Act: -0.0003

Data Index: 444085 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0519. Min Act: -0.0003

Data Index: 32906 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0517. Min Act: -0.0003

Data Index: 213307 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0525. Min Act: -0.0003

Data Index: 400396 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0504. Min Act: -0.0003

Data Index: 871511 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0515. Min Act: -0.0003

Data Index: 185797 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0495. Min Act: -0.0003

Data Index: 477615 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1165156 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0487. Min Act: -0.0003

Data Index: 636315 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0485. Min Act: -0.0003

Data Index: 492329 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1107321 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0478. Min Act: -0.0003

Data Index: 627136 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0470. Min Act: -0.0003

Data Index: 1189241 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0476. Min Act: -0.0003

Data Index: 661745 (C4 (Web Text))

Max Activating Token Index: 748