Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5865 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2299. Min Act: -0.0000

Data Index: 893552 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1493792 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1415863 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1511970 (Python Code)

Max Activating Token Index: 651

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2121. Min Act: -0.0000

Data Index: 604677 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1433232 (Python Code)

Max Activating Token Index: 118

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1517813 (Python Code)

Max Activating Token Index: 115

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1945. Min Act: -0.0000

Data Index: 197855 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1194527 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1470254 (Python Code)

Max Activating Token Index: 310

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1525551 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1414217 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1094740 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1493851 (Python Code)

Max Activating Token Index: 147

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1456613 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1647. Min Act: -0.0000

Data Index: 473239 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1194234 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1559682 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1413968 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1490382 (Python Code)

Max Activating Token Index: 665