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

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

Neuron 3661 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: 0.2197. Min Range: -0.2197

Max Act: 0.2197. Min Act: -0.0000

Data Index: 1090642 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1741. Min Act: -0.0000

Data Index: 241842 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1718. Min Act: -0.0001

Data Index: 1162816 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1631. Min Act: -0.0000

Data Index: 111133 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1471611 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1248234 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1590. Min Act: -0.0000

Data Index: 554510 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1641. Min Act: 0.0000

Data Index: 1213822 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1581. Min Act: -0.0000

Data Index: 764250 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1561. Min Act: -0.0000

Data Index: 389376 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1519. Min Act: -0.0000

Data Index: 609779 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1428. Min Act: -0.0000

Data Index: 9514 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1336098 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1432. Min Act: -0.0000

Data Index: 174786 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1400. Min Act: -0.0000

Data Index: 769841 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1335. Min Act: -0.0001

Data Index: 674817 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1449006 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1309751 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1422. Min Act: -0.0000

Data Index: 447468 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1371. Min Act: 0.0001

Data Index: 1278740 (C4 (Web Text))

Max Activating Token Index: 41