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

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

Neuron 958 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1679. Min Act: -0.0002

Data Index: 403080 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1806. Min Act: -0.0002

Data Index: 164065 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1616. Min Act: -0.0002

Data Index: 928555 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1592. Min Act: -0.0002

Data Index: 1307746 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1534. Min Act: -0.0002

Data Index: 592587 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1445. Min Act: -0.0002

Data Index: 908794 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1463. Min Act: -0.0002

Data Index: 876941 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1031689 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1241760 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1429. Min Act: -0.0002

Data Index: 935418 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1483. Min Act: -0.0002

Data Index: 317024 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1441. Min Act: -0.0002

Data Index: 71859 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1473. Min Act: -0.0002

Data Index: 804679 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1449. Min Act: -0.0002

Data Index: 1030956 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1501. Min Act: -0.0002

Data Index: 412100 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1594. Min Act: -0.0002

Data Index: 466022 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1403. Min Act: -0.0002

Data Index: 431075 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1490. Min Act: -0.0002

Data Index: 1249002 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1396. Min Act: -0.0002

Data Index: 517849 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 0.1806. Min Range: -0.1806

Max Act: 0.1375. Min Act: -0.0002

Data Index: 30865 (C4 (Web Text))

Max Activating Token Index: 740