Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0005

Data Index: 1221857 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1653. Min Act: -0.0005

Data Index: 331200 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1617. Min Act: -0.0005

Data Index: 396539 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1479. Min Act: -0.0005

Data Index: 929813 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1533. Min Act: -0.0005

Data Index: 1198034 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1230. Min Act: -0.0005

Data Index: 1265450 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1472. Min Act: -0.0005

Data Index: 175477 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1503. Min Act: -0.0005

Data Index: 881429 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1509. Min Act: -0.0005

Data Index: 555284 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1459. Min Act: -0.0005

Data Index: 156749 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1431. Min Act: -0.0005

Data Index: 1085630 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1507. Min Act: -0.0005

Data Index: 836864 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1534. Min Act: -0.0005

Data Index: 798438 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1397. Min Act: -0.0005

Data Index: 317351 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1466. Min Act: -0.0005

Data Index: 607126 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1412. Min Act: -0.0005

Data Index: 516206 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1605. Min Act: -0.0005

Data Index: 723881 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1409. Min Act: -0.0005

Data Index: 1291552 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1364. Min Act: -0.0005

Data Index: 936416 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1348. Min Act: -0.0005

Data Index: 275636 (C4 (Web Text))

Max Activating Token Index: 245