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

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

Neuron 5888 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.6867. Min Act: -0.0000

Data Index: 1423128 (Python Code)

Max Activating Token Index: 40

Text #1

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.6141. Min Act: -0.0000

Data Index: 1630564 (Python Code)

Max Activating Token Index: 586

Text #2

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.5538. Min Act: -0.0000

Data Index: 1483548 (Python Code)

Max Activating Token Index: 393

Text #3

Max Range: 4.6867. Min Range: -4.6867

Max Act: 4.1066. Min Act: -0.0000

Data Index: 1622848 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 4.6867. Min Range: -4.6867

Max Act: 3.3468. Min Act: -0.0000

Data Index: 1547020 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 4.6867. Min Range: -4.6867

Max Act: 3.2560. Min Act: -0.0000

Data Index: 1520273 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 4.6867. Min Range: -4.6867

Max Act: 3.5837. Min Act: -0.0000

Data Index: 1395914 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 4.6867. Min Range: -4.6867

Max Act: 3.0636. Min Act: -0.0000

Data Index: 1532373 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.8173. Min Act: -0.0000

Data Index: 1530858 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.8024. Min Act: -0.0000

Data Index: 1549263 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.5355. Min Act: -0.0000

Data Index: 1607793 (Python Code)

Max Activating Token Index: 94

Text #11

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.5449. Min Act: -0.0000

Data Index: 1612840 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1385675 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.5107. Min Act: -0.0000

Data Index: 1610868 (Python Code)

Max Activating Token Index: 802

Text #14

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.5790. Min Act: -0.0000

Data Index: 1563986 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.4217. Min Act: -0.0000

Data Index: 1565873 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.6731. Min Act: -0.0000

Data Index: 1462999 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.4047. Min Act: -0.0000

Data Index: 1372745 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.5271. Min Act: -0.0000

Data Index: 1519364 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 4.6867. Min Range: -4.6867

Max Act: 2.5339. Min Act: -0.0000

Data Index: 1421483 (Python Code)

Max Activating Token Index: 147