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

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

Neuron 782 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1385091 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1610. Min Act: -0.0001

Data Index: 527875 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1655. Min Act: -0.0001

Data Index: 675787 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1170731 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1277671 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1596. Min Act: -0.0001

Data Index: 772928 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1189594 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1126431 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1427. Min Act: -0.0001

Data Index: 894848 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1495. Min Act: -0.0001

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1477. Min Act: -0.0001

Data Index: 366560 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1397. Min Act: -0.0001

Data Index: 838024 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1406621 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1402. Min Act: -0.0001

Data Index: 541522 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1413339 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1307. Min Act: -0.0001

Data Index: 966130 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1490. Min Act: -0.0001

Data Index: 966231 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1373. Min Act: -0.0001

Data Index: 47658 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1428. Min Act: -0.0001

Data Index: 65996 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.1756. Min Range: -0.1756

Max Act: 0.1469. Min Act: -0.0001

Data Index: 644937 (C4 (Web Text))

Max Activating Token Index: 281