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

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

Neuron 1463 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1929. Min Act: -0.0001

Data Index: 811054 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1820. Min Act: -0.0001

Data Index: 15281 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1813. Min Act: -0.0001

Data Index: 629214 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1557. Min Act: -0.0001

Data Index: 389327 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1338269 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1209875 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1499. Min Act: -0.0001

Data Index: 282607 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1405. Min Act: -0.0001

Data Index: 304215 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1392. Min Act: -0.0001

Data Index: 99003 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1664. Min Act: -0.0001

Data Index: 797104 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1408. Min Act: -0.0001

Data Index: 150666 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1421. Min Act: -0.0001

Data Index: 835713 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1393. Min Act: -0.0001

Data Index: 442333 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1343. Min Act: -0.0001

Data Index: 549465 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1080346 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1432. Min Act: -0.0001

Data Index: 213234 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1373. Min Act: -0.0001

Data Index: 238031 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1321. Min Act: -0.0001

Data Index: 307699 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1316. Min Act: -0.0001

Data Index: 70168 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1359. Min Act: -0.0001

Data Index: 582932 (C4 (Web Text))

Max Activating Token Index: 951