Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5143 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.2551. Min Act: -0.0001

Data Index: 99086 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1745. Min Act: -0.0001

Data Index: 951642 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1251318 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1686. Min Act: -0.0001

Data Index: 736332 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1304728 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1622. Min Act: -0.0001

Data Index: 971264 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1571. Min Act: -0.0001

Data Index: 555889 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1604. Min Act: -0.0001

Data Index: 946543 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1541. Min Act: -0.0001

Data Index: 784152 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1124719 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1508. Min Act: -0.0001

Data Index: 421569 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1326. Min Act: -0.0001

Data Index: 487452 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1536. Min Act: -0.0001

Data Index: 973614 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1728. Min Act: -0.0001

Data Index: 796588 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1359. Min Act: -0.0001

Data Index: 945411 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1382. Min Act: -0.0001

Data Index: 790964 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1316. Min Act: -0.0001

Data Index: 554530 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1361. Min Act: -0.0001

Data Index: 236043 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1287628 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.2551. Min Range: -0.2551

Max Act: 0.1428. Min Act: -0.0001

Data Index: 212689 (C4 (Web Text))

Max Activating Token Index: 336