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

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

Neuron 5543 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0000

Data Index: 229874 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1126927 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1886. Min Act: -0.0000

Data Index: 372118 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1445024 (Python Code)

Max Activating Token Index: 623

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1664. Min Act: 0.0000

Data Index: 1233703 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1185112 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1561259 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1539. Min Act: -0.0000

Data Index: 241262 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1457. Min Act: -0.0000

Data Index: 458019 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1442. Min Act: -0.0000

Data Index: 138379 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1521932 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1348. Min Act: -0.0000

Data Index: 434066 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1383. Min Act: -0.0000

Data Index: 481443 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1366. Min Act: -0.0000

Data Index: 619369 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1293. Min Act: -0.0000

Data Index: 395980 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1294. Min Act: -0.0000

Data Index: 413299 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1079. Min Act: 0.0000

Data Index: 660050 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1236. Min Act: -0.0000

Data Index: 415789 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1478878 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1247. Min Act: -0.0000

Data Index: 374378 (C4 (Web Text))

Max Activating Token Index: 418