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

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

Neuron 506 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1580. Min Act: -0.0005

Data Index: 236821 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1615. Min Act: -0.0005

Data Index: 1177288 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0005

Data Index: 207366 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1545. Min Act: -0.0005

Data Index: 1005865 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1458. Min Act: -0.0005

Data Index: 111800 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1433. Min Act: -0.0005

Data Index: 658877 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1458. Min Act: -0.0005

Data Index: 743245 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1432. Min Act: -0.0005

Data Index: 736118 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1486. Min Act: -0.0005

Data Index: 703523 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1363. Min Act: -0.0005

Data Index: 1293607 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1345. Min Act: -0.0005

Data Index: 1160781 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1447. Min Act: -0.0005

Data Index: 333942 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1323. Min Act: -0.0005

Data Index: 926464 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1452. Min Act: -0.0005

Data Index: 542609 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1308. Min Act: -0.0005

Data Index: 765477 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1364. Min Act: -0.0005

Data Index: 359692 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1393. Min Act: -0.0005

Data Index: 1089737 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1345. Min Act: -0.0005

Data Index: 616225 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1310. Min Act: -0.0005

Data Index: 727435 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1347. Min Act: -0.0005

Data Index: 62938 (C4 (Web Text))

Max Activating Token Index: 686