Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1614024 (Python Code)

Max Activating Token Index: 478

Text #1

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1792. Min Act: -0.0001

Data Index: 1577690 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1447561 (Python Code)

Max Activating Token Index: 102

Text #3

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1506415 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1375970 (Python Code)

Max Activating Token Index: 286

Text #5

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1617580 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1633998 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1459918 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1384028 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1529720 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1626. Min Act: -0.0001

Data Index: 1515589 (Python Code)

Max Activating Token Index: 342

Text #11

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1561555 (Python Code)

Max Activating Token Index: 966

Text #12

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1500272 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1530316 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1606464 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1556859 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1412392 (Python Code)

Max Activating Token Index: 205

Text #17

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1530044 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1406978 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.1792. Min Range: -0.1792

Max Act: 0.1457. Min Act: -0.0001

Data Index: 1569542 (Python Code)

Max Activating Token Index: 222