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

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

Neuron 3459 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: 0.1725. Min Range: -0.1725

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1118253 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1657. Min Act: -0.0000

Data Index: 438328 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1119830 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1596. Min Act: -0.0000

Data Index: 565282 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1489. Min Act: -0.0000

Data Index: 354884 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1203546 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1249432 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1467. Min Act: -0.0000

Data Index: 871862 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1505. Min Act: -0.0000

Data Index: 637952 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1201122 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1467. Min Act: -0.0000

Data Index: 652948 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1467. Min Act: -0.0000

Data Index: 672471 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1420. Min Act: -0.0000

Data Index: 755156 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1159310 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1445. Min Act: -0.0000

Data Index: 236954 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1331. Min Act: -0.0000

Data Index: 194769 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1057021 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1315. Min Act: -0.0000

Data Index: 546715 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1294. Min Act: -0.0000

Data Index: 129590 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1336. Min Act: -0.0000

Data Index: 814772 (C4 (Web Text))

Max Activating Token Index: 358