Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1417534 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1614284 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1856. Min Act: -0.0001

Data Index: 607874 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1054900 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1503577 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1694. Min Act: -0.0001

Data Index: 219661 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1454510 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1270292 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1388698 (Python Code)

Max Activating Token Index: 121

Text #9

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1789. Min Act: -0.0001

Data Index: 645754 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1652. Min Act: -0.0001

Data Index: 404511 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1485603 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1473. Min Act: 0.0000

Data Index: 1540731 (Python Code)

Max Activating Token Index: 548

Text #13

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1048808 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1400510 (Python Code)

Max Activating Token Index: 708

Text #15

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1130330 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1535. Min Act: -0.0001

Data Index: 212003 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1215573 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1548620 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.2431. Min Range: -0.2431

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1391324 (Python Code)

Max Activating Token Index: 504