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

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

Neuron 593 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: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0006

Data Index: 666898 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0470. Min Act: -0.0006

Data Index: 1144621 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0414. Min Act: -0.0006

Data Index: 148953 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0404. Min Act: -0.0006

Data Index: 203087 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0399. Min Act: -0.0006

Data Index: 570611 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0406. Min Act: -0.0006

Data Index: 745406 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0409. Min Act: -0.0006

Data Index: 792141 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0405. Min Act: -0.0006

Data Index: 755186 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0395. Min Act: -0.0006

Data Index: 770218 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0402. Min Act: -0.0006

Data Index: 935060 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0392. Min Act: -0.0006

Data Index: 799446 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0377. Min Act: -0.0006

Data Index: 541035 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0388. Min Act: -0.0006

Data Index: 1236278 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1331938 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1176681 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0368. Min Act: -0.0006

Data Index: 461387 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0372. Min Act: -0.0006

Data Index: 1077155 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0376. Min Act: -0.0006

Data Index: 475622 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0351. Min Act: -0.0006

Data Index: 808831 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0364. Min Act: -0.0006

Data Index: 330290 (C4 (Web Text))

Max Activating Token Index: 993