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

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

Neuron 1437 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1595553 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1415057 (Python Code)

Max Activating Token Index: 468

Text #2

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1474030 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1620632 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1641907 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1511646 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1558059 (Python Code)

Max Activating Token Index: 518

Text #7

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1548707 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1466020 (Python Code)

Max Activating Token Index: 954

Text #9

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1415215 (Python Code)

Max Activating Token Index: 559

Text #10

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1473394 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1402846 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1429923 (Python Code)

Max Activating Token Index: 624

Text #13

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1366302 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1646547 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1589070 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1401061 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1649748 (Python Code)

Max Activating Token Index: 391

Text #18

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1496238 (Python Code)

Max Activating Token Index: 637

Text #19

Max Range: 0.2000. Min Range: -0.2000

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1589124 (Python Code)

Max Activating Token Index: 760