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

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

Neuron 1027 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: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1260114 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1067784 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1009330 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0379. Min Act: -0.0000

Data Index: 998812 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0373. Min Act: -0.0002

Data Index: 667476 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1183126 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0396. Min Act: -0.0002

Data Index: 177603 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0371. Min Act: -0.0002

Data Index: 909099 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1168571 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0357. Min Act: -0.0002

Data Index: 885776 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0344. Min Act: -0.0002

Data Index: 431346 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1028226 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1342671 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1297817 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0353. Min Act: -0.0002

Data Index: 120199 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1428534 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1222766 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0411. Min Act: -0.0002

Data Index: 158127 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0341. Min Act: -0.0001

Data Index: 316446 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0376. Min Act: -0.0002

Data Index: 970028 (C4 (Web Text))

Max Activating Token Index: 753