Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 961 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: 0.0000

Data Index: 1110770 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1883. Min Act: -0.0001

Data Index: 579970 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1770. Min Act: -0.0001

Data Index: 710947 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1769. Min Act: 0.0001

Data Index: 1359411 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1699. Min Act: 0.0000

Data Index: 32524 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1604. Min Act: -0.0001

Data Index: 329783 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1265106 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1581. Min Act: -0.0001

Data Index: 747960 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1570. Min Act: -0.0001

Data Index: 704895 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1132639 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1636. Min Act: -0.0001

Data Index: 753050 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1496. Min Act: -0.0001

Data Index: 889617 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1082890 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1492. Min Act: 0.0000

Data Index: 73338 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1405. Min Act: -0.0000

Data Index: 785764 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1480. Min Act: -0.0000

Data Index: 824120 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1376. Min Act: -0.0001

Data Index: 861745 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1365. Min Act: -0.0000

Data Index: 594047 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1394. Min Act: -0.0001

Data Index: 164067 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1437. Min Act: -0.0001

Data Index: 358857 (C4 (Web Text))

Max Activating Token Index: 288