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

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

Neuron 59 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1604874 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6283. Min Act: -0.0001

Data Index: 1571327 (Python Code)

Max Activating Token Index: 58

Text #2

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6369. Min Act: -0.0001

Data Index: 1587742 (Python Code)

Max Activating Token Index: 515

Text #3

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6304. Min Act: -0.0001

Data Index: 1362965 (Python Code)

Max Activating Token Index: 523

Text #4

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5745. Min Act: -0.0001

Data Index: 1539439 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6418. Min Act: -0.0001

Data Index: 1472646 (Python Code)

Max Activating Token Index: 871

Text #6

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6189. Min Act: -0.0001

Data Index: 1364155 (Python Code)

Max Activating Token Index: 687

Text #7

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6097. Min Act: -0.0001

Data Index: 1570741 (Python Code)

Max Activating Token Index: 265

Text #8

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5975. Min Act: -0.0001

Data Index: 1575847 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1497492 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5643. Min Act: -0.0001

Data Index: 1394815 (Python Code)

Max Activating Token Index: 916

Text #11

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1600677 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6190. Min Act: -0.0001

Data Index: 1587348 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5465. Min Act: -0.0001

Data Index: 1399902 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5528. Min Act: -0.0001

Data Index: 1610937 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5446. Min Act: -0.0001

Data Index: 1453635 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1577732 (Python Code)

Max Activating Token Index: 569

Text #17

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.6457. Min Act: -0.0001

Data Index: 1540204 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5601. Min Act: -0.0001

Data Index: 1636085 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 0.8325. Min Range: -0.8325

Max Act: 0.5336. Min Act: -0.0001

Data Index: 1642395 (Python Code)

Max Activating Token Index: 1011