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

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

Neuron 1672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1386331 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1619509 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1160113 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1769. Min Act: -0.0000

Data Index: 868568 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1722. Min Act: -0.0000

Data Index: 207640 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1703. Min Act: -0.0001

Data Index: 1528724 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1302526 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1491073 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1431846 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1457047 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1412133 (Python Code)

Max Activating Token Index: 576

Text #11

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1656173 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1510. Min Act: -0.0000

Data Index: 322929 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1617. Min Act: -0.0000

Data Index: 763859 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1593815 (Python Code)

Max Activating Token Index: 370

Text #15

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1372316 (Python Code)

Max Activating Token Index: 38

Text #16

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1622782 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1529. Min Act: -0.0000

Data Index: 1531028 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1553139 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1436702 (Python Code)

Max Activating Token Index: 453