Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3779 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0003

Data Index: 1076891 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1707. Min Act: -0.0002

Data Index: 174916 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1648. Min Act: -0.0002

Data Index: 118205 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1530. Min Act: -0.0003

Data Index: 1271731 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1425. Min Act: -0.0002

Data Index: 434012 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1473. Min Act: -0.0002

Data Index: 741277 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1394. Min Act: -0.0003

Data Index: 591412 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1422. Min Act: -0.0003

Data Index: 1080515 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1020086 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1424. Min Act: -0.0003

Data Index: 904581 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1476. Min Act: -0.0002

Data Index: 29303 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1340. Min Act: -0.0003

Data Index: 97528 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1391. Min Act: -0.0003

Data Index: 267503 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1377. Min Act: -0.0003

Data Index: 235224 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1384. Min Act: -0.0003

Data Index: 1013374 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1417. Min Act: -0.0003

Data Index: 404394 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1314. Min Act: -0.0002

Data Index: 904290 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1367. Min Act: -0.0003

Data Index: 837376 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1318. Min Act: -0.0003

Data Index: 303314 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1154582 (C4 (Web Text))

Max Activating Token Index: 74