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

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

Neuron 3350 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1650545 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1604791 (Python Code)

Max Activating Token Index: 621

Text #2

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1422204 (Python Code)

Max Activating Token Index: 726

Text #3

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1499466 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1531988 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1416185 (Python Code)

Max Activating Token Index: 461

Text #6

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1506272 (Python Code)

Max Activating Token Index: 824

Text #7

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1559561 (Python Code)

Max Activating Token Index: 919

Text #8

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1556153 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1427323 (Python Code)

Max Activating Token Index: 476

Text #10

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1462614 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1459949 (Python Code)

Max Activating Token Index: 1020

Text #12

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1602127 (Python Code)

Max Activating Token Index: 592

Text #13

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1402670 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1589. Min Act: -0.0001

Data Index: 1533021 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1621936 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1401577 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1578450 (Python Code)

Max Activating Token Index: 956

Text #18

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1654312 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1514. Min Act: -0.0001

Data Index: 1414877 (Python Code)

Max Activating Token Index: 482