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

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

Neuron 5776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1637932 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1408653 (Python Code)

Max Activating Token Index: 595

Text #2

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1605097 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1791. Min Act: -0.0000

Data Index: 982081 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1415942 (Python Code)

Max Activating Token Index: 195

Text #5

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1640590 (Python Code)

Max Activating Token Index: 279

Text #6

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1701. Min Act: -0.0000

Data Index: 1467758 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1612035 (Python Code)

Max Activating Token Index: 381

Text #8

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1559568 (Python Code)

Max Activating Token Index: 644

Text #9

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1398350 (Python Code)

Max Activating Token Index: 757

Text #10

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1343993 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1438983 (Python Code)

Max Activating Token Index: 716

Text #12

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1517. Min Act: -0.0000

Data Index: 754342 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1525. Min Act: -0.0000

Data Index: 757364 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1488094 (Python Code)

Max Activating Token Index: 852

Text #15

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1614195 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1346. Min Act: -0.0000

Data Index: 775751 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1473197 (Python Code)

Max Activating Token Index: 236

Text #18

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1651128 (Python Code)

Max Activating Token Index: 41

Text #19

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1369400 (Python Code)

Max Activating Token Index: 215