Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1799 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0001

Data Index: 765732 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1659. Min Act: -0.0001

Data Index: 352108 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1724. Min Act: -0.0001

Data Index: 75578 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1523. Min Act: -0.0001

Data Index: 816871 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1572. Min Act: -0.0001

Data Index: 576174 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1216518 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1555. Min Act: -0.0001

Data Index: 425756 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1498. Min Act: -0.0001

Data Index: 258287 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1484. Min Act: -0.0001

Data Index: 154948 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1429. Min Act: -0.0001

Data Index: 693631 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1311355 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1411. Min Act: -0.0001

Data Index: 345790 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1414. Min Act: -0.0001

Data Index: 46008 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1392. Min Act: -0.0001

Data Index: 356933 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1334. Min Act: -0.0002

Data Index: 747890 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1277. Min Act: -0.0002

Data Index: 125740 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1383. Min Act: -0.0001

Data Index: 166485 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1425. Min Act: -0.0001

Data Index: 555807 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1420. Min Act: -0.0001

Data Index: 500027 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1408. Min Act: -0.0001

Data Index: 402567 (C4 (Web Text))

Max Activating Token Index: 156