Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.2042. Min Act: -0.0000

Data Index: 343130 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1378. Min Act: -0.0000

Data Index: 673783 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1412. Min Act: -0.0000

Data Index: 120772 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1237282 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1375. Min Act: -0.0000

Data Index: 410507 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1424. Min Act: -0.0000

Data Index: 788904 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1181026 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1401. Min Act: -0.0000

Data Index: 498944 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1391. Min Act: -0.0000

Data Index: 454132 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1298. Min Act: -0.0000

Data Index: 980003 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1260. Min Act: -0.0000

Data Index: 539893 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1404. Min Act: -0.0000

Data Index: 679871 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1355. Min Act: -0.0000

Data Index: 412034 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1290. Min Act: -0.0000

Data Index: 746973 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1325. Min Act: -0.0000

Data Index: 803933 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1359. Min Act: -0.0000

Data Index: 495951 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1349. Min Act: -0.0000

Data Index: 587953 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1331. Min Act: -0.0000

Data Index: 907544 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1334. Min Act: -0.0000

Data Index: 339886 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1176. Min Act: -0.0000

Data Index: 67288 (C4 (Web Text))

Max Activating Token Index: 611