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

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

Neuron 2302 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1823. Min Range: -2.1823

Max Act: 2.1823. Min Act: -0.0000

Data Index: 935959 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.9558. Min Act: -0.0000

Data Index: 516243 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.9288. Min Act: -0.0000

Data Index: 681928 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.8283. Min Act: -0.0000

Data Index: 430821 (C4 (Web Text))

Max Activating Token Index: 580

Text #4

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.8209. Min Act: -0.0000

Data Index: 633241 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.7181. Min Act: -0.0000

Data Index: 1310166 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.7957. Min Act: -0.0000

Data Index: 252671 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.7478. Min Act: -0.0000

Data Index: 139927 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.7429. Min Act: -0.0000

Data Index: 832419 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1057451 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.6877. Min Act: -0.0000

Data Index: 582369 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.6056. Min Act: -0.0000

Data Index: 1475 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.6731. Min Act: -0.0000

Data Index: 472760 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.7096. Min Act: -0.0000

Data Index: 1136959 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1261971 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.5260. Min Act: -0.0000

Data Index: 214509 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.5714. Min Act: -0.0000

Data Index: 923850 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.6494. Min Act: -0.0000

Data Index: 499228 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.5745. Min Act: -0.0000

Data Index: 219432 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 2.1823. Min Range: -2.1823

Max Act: 1.5380. Min Act: -0.0000

Data Index: 72785 (C4 (Web Text))

Max Activating Token Index: 124