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

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

Neuron 808 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1460. Min Act: -0.0001

Data Index: 504456 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1081276 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1058638 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1378. Min Act: -0.0001

Data Index: 287137 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1394. Min Act: -0.0001

Data Index: 68327 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1390. Min Act: -0.0001

Data Index: 699621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1357. Min Act: -0.0001

Data Index: 421004 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1357. Min Act: -0.0001

Data Index: 591715 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1360. Min Act: -0.0001

Data Index: 413637 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1127890 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1313. Min Act: -0.0001

Data Index: 739920 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1331. Min Act: -0.0001

Data Index: 102070 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1300. Min Act: -0.0001

Data Index: 439202 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1339. Min Act: -0.0001

Data Index: 852889 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1315. Min Act: -0.0001

Data Index: 578890 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1322. Min Act: -0.0001

Data Index: 281422 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1179979 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1272. Min Act: -0.0001

Data Index: 852745 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1272. Min Act: -0.0001

Data Index: 8820 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1299. Min Act: -0.0001

Data Index: 923826 (C4 (Web Text))

Max Activating Token Index: 582