Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 719 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1401983 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1491323 (Python Code)

Max Activating Token Index: 240

Text #2

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1442692 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1400053 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1548326 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1637850 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1601. Min Act: -0.0001

Data Index: 1504986 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1552880 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1360589 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1379268 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1557281 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1504780 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1481662 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1509534 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1627576 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1480. Min Act: -0.0001

Data Index: 1517232 (Python Code)

Max Activating Token Index: 855

Text #16

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1650041 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1367831 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1621825 (Python Code)

Max Activating Token Index: 99

Text #19

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1503. Min Act: -0.0001

Data Index: 1511032 (Python Code)

Max Activating Token Index: 363