Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5102 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1571. Min Act: -0.0000

Data Index: 709653 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1672. Min Act: -0.0000

Data Index: 407458 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1558. Min Act: -0.0000

Data Index: 373876 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1012286 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1583. Min Act: -0.0000

Data Index: 65493 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1346353 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1580. Min Act: -0.0000

Data Index: 827688 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1570. Min Act: -0.0000

Data Index: 544678 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1511. Min Act: -0.0000

Data Index: 941148 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1546. Min Act: -0.0000

Data Index: 196450 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1527. Min Act: -0.0000

Data Index: 47846 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1409. Min Act: -0.0000

Data Index: 673178 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1445. Min Act: -0.0000

Data Index: 775227 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1304476 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1440. Min Act: -0.0000

Data Index: 18521 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1019165 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1213848 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1359. Min Act: -0.0000

Data Index: 812539 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1308. Min Act: -0.0000

Data Index: 342384 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.1672. Min Range: -0.1672

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1201571 (C4 (Web Text))

Max Activating Token Index: 398