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

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

Neuron 817 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: 0.1744. Min Range: -0.1744

Max Act: 0.1646. Min Act: -0.0002

Data Index: 238735 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0002

Data Index: 1153607 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1578. Min Act: -0.0002

Data Index: 521599 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1544. Min Act: -0.0002

Data Index: 845868 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1528. Min Act: -0.0002

Data Index: 377773 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1505. Min Act: -0.0002

Data Index: 814654 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1510. Min Act: -0.0002

Data Index: 815182 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1129717 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1478. Min Act: -0.0002

Data Index: 383914 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1499. Min Act: -0.0002

Data Index: 686790 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1476. Min Act: -0.0002

Data Index: 495845 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1418. Min Act: -0.0002

Data Index: 1041873 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1412. Min Act: -0.0002

Data Index: 1263906 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1490. Min Act: -0.0002

Data Index: 759558 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1515. Min Act: -0.0002

Data Index: 471393 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1343. Min Act: -0.0002

Data Index: 678191 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1408. Min Act: -0.0002

Data Index: 842349 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1435. Min Act: -0.0002

Data Index: 542191 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1385. Min Act: -0.0002

Data Index: 1007326 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1496. Min Act: -0.0002

Data Index: 512623 (C4 (Web Text))

Max Activating Token Index: 283