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

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

Neuron 4844 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1503516 (Python Code)

Max Activating Token Index: 789

Text #1

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1510315 (Python Code)

Max Activating Token Index: 671

Text #2

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1590787 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5220. Min Act: -0.0001

Data Index: 1515236 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1390799 (Python Code)

Max Activating Token Index: 272

Text #5

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1446663 (Python Code)

Max Activating Token Index: 652

Text #6

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1377880 (Python Code)

Max Activating Token Index: 847

Text #7

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1460443 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1638337 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1449459 (Python Code)

Max Activating Token Index: 903

Text #10

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1550230 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5239. Min Act: -0.0000

Data Index: 1645426 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1365096 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1625413 (Python Code)

Max Activating Token Index: 708

Text #14

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1468924 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1641307 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1565483 (Python Code)

Max Activating Token Index: 888

Text #17

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1498911 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1423036 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 0.5616. Min Range: -0.5616

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1479073 (Python Code)

Max Activating Token Index: 290