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

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

Neuron 1176 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1844. Min Act: -0.0001

Data Index: 1446350 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1873. Min Act: -0.0001

Data Index: 1493656 (Python Code)

Max Activating Token Index: 815

Text #2

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1877. Min Act: -0.0001

Data Index: 36863 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1492882 (Python Code)

Max Activating Token Index: 634

Text #4

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1741. Min Act: 0.0000

Data Index: 1364126 (Python Code)

Max Activating Token Index: 1022

Text #5

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1565835 (Python Code)

Max Activating Token Index: 273

Text #6

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1611324 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1503998 (Python Code)

Max Activating Token Index: 607

Text #8

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1403671 (Python Code)

Max Activating Token Index: 927

Text #9

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1408271 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1603. Min Act: -0.0001

Data Index: 1608949 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1488646 (Python Code)

Max Activating Token Index: 746

Text #12

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1580225 (Python Code)

Max Activating Token Index: 838

Text #13

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1511. Min Act: -0.0001

Data Index: 1515913 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1603470 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1648948 (Python Code)

Max Activating Token Index: 845

Text #16

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1614852 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1488175 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1539901 (Python Code)

Max Activating Token Index: 804

Text #19

Max Range: 0.1877. Min Range: -0.1877

Max Act: 0.0625. Min Act: -0.0001

Data Index: 314530 (C4 (Web Text))

Max Activating Token Index: 632