Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2288 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1338893 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0000

Data Index: 866255 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1801. Min Act: -0.0000

Data Index: 867306 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1783. Min Act: -0.0000

Data Index: 270675 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1706. Min Act: -0.0000

Data Index: 613381 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1714. Min Act: -0.0000

Data Index: 981418 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1609. Min Act: -0.0000

Data Index: 88440 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1582. Min Act: -0.0000

Data Index: 942710 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1583. Min Act: -0.0000

Data Index: 385930 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1626. Min Act: -0.0000

Data Index: 897366 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1647. Min Act: -0.0000

Data Index: 560698 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1359461 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1633. Min Act: -0.0000

Data Index: 614919 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1502. Min Act: -0.0000

Data Index: 15032 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1550. Min Act: -0.0000

Data Index: 34776 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1496. Min Act: -0.0000

Data Index: 215051 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1541. Min Act: -0.0000

Data Index: 30616 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1591. Min Act: -0.0000

Data Index: 943188 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1234. Min Act: -0.0000

Data Index: 1347833 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1559. Min Act: -0.0000

Data Index: 1129913 (C4 (Web Text))

Max Activating Token Index: 99