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

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

Neuron 1917 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1551146 (Python Code)

Max Activating Token Index: 930

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0461. Min Act: -0.0002

Data Index: 1514663 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0458. Min Act: -0.0001

Data Index: 936345 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1651998 (Python Code)

Max Activating Token Index: 769

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1490245 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1631687 (Python Code)

Max Activating Token Index: 770

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1606376 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1417205 (Python Code)

Max Activating Token Index: 100

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1425608 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1599215 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1502078 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1502484 (Python Code)

Max Activating Token Index: 361

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1479290 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1493568 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1486341 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0386. Min Act: -0.0002

Data Index: 29609 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1438136 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1609896 (Python Code)

Max Activating Token Index: 718

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1481208 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1587110 (Python Code)

Max Activating Token Index: 78