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

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

Neuron 2253 in Layer 5

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: 949906 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1679. Min Act: -0.0001

Data Index: 677602 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1707. Min Act: -0.0001

Data Index: 244494 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1073049 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1702. Min Act: -0.0001

Data Index: 831771 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1667. Min Act: -0.0001

Data Index: 100326 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1531. Min Act: -0.0001

Data Index: 837525 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1483. Min Act: -0.0001

Data Index: 818601 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1412. Min Act: -0.0001

Data Index: 908768 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1549. Min Act: -0.0001

Data Index: 558822 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1194735 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1610. Min Act: 0.0000

Data Index: 994191 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1420. Min Act: -0.0000

Data Index: 924764 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1432. Min Act: -0.0001

Data Index: 627591 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1363. Min Act: -0.0001

Data Index: 742603 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1335. Min Act: -0.0001

Data Index: 284042 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1358. Min Act: -0.0001

Data Index: 455055 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1273. Min Act: -0.0001

Data Index: 939758 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1237. Min Act: -0.0001

Data Index: 207122 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1275. Min Act: -0.0001

Data Index: 504721 (C4 (Web Text))

Max Activating Token Index: 307