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

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

Neuron 1271 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: 0.0478. Min Range: -0.0478

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1293464 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1088580 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1249240 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1502067 (Python Code)

Max Activating Token Index: 608

Text #4

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0423. Min Act: -0.0002

Data Index: 628107 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0401. Min Act: -0.0002

Data Index: 455796 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1097791 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1411735 (Python Code)

Max Activating Token Index: 567

Text #8

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1620236 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1480606 (Python Code)

Max Activating Token Index: 981

Text #10

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0395. Min Act: -0.0002

Data Index: 229434 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0383. Min Act: -0.0002

Data Index: 154209 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0381. Min Act: -0.0002

Data Index: 531861 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0383. Min Act: -0.0002

Data Index: 742281 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1081930 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1514391 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1534686 (Python Code)

Max Activating Token Index: 627

Text #17

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1553122 (Python Code)

Max Activating Token Index: 168

Text #18

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1604417 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 0.0478. Min Range: -0.0478

Max Act: 0.0366. Min Act: -0.0002

Data Index: 334891 (C4 (Web Text))

Max Activating Token Index: 740