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

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

Neuron 4942 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1862. Min Act: -0.0000

Data Index: 224766 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1011476 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1562221 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1517832 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1552. Min Act: -0.0000

Data Index: 997738 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1616. Min Act: -0.0000

Data Index: 795281 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1570. Min Act: -0.0000

Data Index: 537163 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1108433 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1466741 (Python Code)

Max Activating Token Index: 942

Text #9

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1467. Min Act: -0.0000

Data Index: 877913 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1488. Min Act: -0.0000

Data Index: 19763 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1371224 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1515. Min Act: -0.0000

Data Index: 525913 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1430601 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1460. Min Act: -0.0000

Data Index: 768067 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1495100 (Python Code)

Max Activating Token Index: 733

Text #16

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1556470 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1272889 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1391791 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 0.1862. Min Range: -0.1862

Max Act: 0.1397. Min Act: -0.0000

Data Index: 729124 (C4 (Web Text))

Max Activating Token Index: 241