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

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

Neuron 1408 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1533520 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1630260 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4684. Min Act: -0.0001

Data Index: 161311 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1399691 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1655629 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1368565 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1516913 (Python Code)

Max Activating Token Index: 768

Text #7

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1460653 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1623953 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1586742 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1450208 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1650187 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1637059 (Python Code)

Max Activating Token Index: 894

Text #13

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4303. Min Act: -0.0001

Data Index: 1395066 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4322. Min Act: -0.0001

Data Index: 108043 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1625270 (Python Code)

Max Activating Token Index: 1009

Text #16

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4227. Min Act: -0.0001

Data Index: 1655719 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.3604. Min Act: -0.0001

Data Index: 1210423 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4130. Min Act: -0.0001

Data Index: 638898 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.5429. Min Range: -0.5429

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1602131 (Python Code)

Max Activating Token Index: 306