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

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

Neuron 1440 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: 0.1644. Min Range: -0.1644

Max Act: 0.1644. Min Act: -0.0002

Data Index: 1466638 (Python Code)

Max Activating Token Index: 215

Text #1

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1449. Min Act: -0.0002

Data Index: 1538327 (Python Code)

Max Activating Token Index: 420

Text #2

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1559. Min Act: -0.0002

Data Index: 1411328 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1492. Min Act: -0.0002

Data Index: 917298 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1565. Min Act: -0.0002

Data Index: 1655538 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1522. Min Act: -0.0002

Data Index: 1651379 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1531. Min Act: -0.0002

Data Index: 358076 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1567589 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1510409 (Python Code)

Max Activating Token Index: 798

Text #9

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1631986 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1430. Min Act: -0.0002

Data Index: 1538372 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1385778 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1388. Min Act: -0.0002

Data Index: 442443 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1382. Min Act: -0.0002

Data Index: 997328 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1417105 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1411087 (Python Code)

Max Activating Token Index: 754

Text #16

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1477. Min Act: -0.0002

Data Index: 1430820 (Python Code)

Max Activating Token Index: 667

Text #17

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1605004 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1355. Min Act: -0.0002

Data Index: 1433136 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.1644. Min Range: -0.1644

Max Act: 0.1375. Min Act: -0.0002

Data Index: 1616340 (Python Code)

Max Activating Token Index: 912