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

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

Neuron 3520 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: 4.6227. Min Range: -4.6227

Max Act: 4.5209. Min Act: -0.0000

Data Index: 1515639 (Python Code)

Max Activating Token Index: 1004

Text #1

Max Range: 4.6227. Min Range: -4.6227

Max Act: 4.6227. Min Act: -0.0000

Data Index: 1462209 (Python Code)

Max Activating Token Index: 948

Text #2

Max Range: 4.6227. Min Range: -4.6227

Max Act: 4.1407. Min Act: -0.0000

Data Index: 1441476 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.8546. Min Act: -0.0000

Data Index: 1398488 (Python Code)

Max Activating Token Index: 728

Text #4

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.7625. Min Act: -0.0000

Data Index: 1611125 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.8954. Min Act: -0.0000

Data Index: 1625837 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.5438. Min Act: -0.0000

Data Index: 1565078 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.7874. Min Act: -0.0000

Data Index: 1623871 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1363214 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.4229. Min Act: -0.0000

Data Index: 1653120 (Python Code)

Max Activating Token Index: 120

Text #10

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.5210. Min Act: -0.0000

Data Index: 1442265 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.5404. Min Act: -0.0000

Data Index: 1394032 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.8317. Min Act: -0.0000

Data Index: 1462855 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.5167. Min Act: -0.0000

Data Index: 1475560 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.2891. Min Act: -0.0000

Data Index: 1475831 (Python Code)

Max Activating Token Index: 807

Text #15

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.2637. Min Act: -0.0000

Data Index: 1443890 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.5633. Min Act: -0.0000

Data Index: 1391483 (Python Code)

Max Activating Token Index: 894

Text #17

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.5652. Min Act: -0.0000

Data Index: 1427178 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.2355. Min Act: -0.0000

Data Index: 1527183 (Python Code)

Max Activating Token Index: 649

Text #19

Max Range: 4.6227. Min Range: -4.6227

Max Act: 3.0903. Min Act: -0.0000

Data Index: 1579341 (Python Code)

Max Activating Token Index: 801