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

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

Neuron 2405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.9604. Min Act: -0.0000

Data Index: 1649803 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1541073 (Python Code)

Max Activating Token Index: 125

Text #2

Max Range: 1.9604. Min Range: -1.9604

Max Act: 1.0106. Min Act: -0.0000

Data Index: 557478 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1445302 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1294702 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7526. Min Act: -0.0000

Data Index: 1572193 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7554. Min Act: -0.0000

Data Index: 206082 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1201813 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1436774 (Python Code)

Max Activating Token Index: 949

Text #9

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7181. Min Act: -0.0000

Data Index: 901255 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7354. Min Act: -0.0000

Data Index: 403424 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6829. Min Act: -0.0000

Data Index: 791703 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7274. Min Act: -0.0000

Data Index: 724317 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6823. Min Act: -0.0000

Data Index: 1142504 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6925. Min Act: -0.0000

Data Index: 547506 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1496088 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.7268. Min Act: -0.0000

Data Index: 504906 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6570. Min Act: -0.0000

Data Index: 545997 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1070726 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 1.9604. Min Range: -1.9604

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1311373 (C4 (Web Text))

Max Activating Token Index: 680