Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2807 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0003

Data Index: 1654464 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1647183 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0465. Min Act: -0.0003

Data Index: 1527910 (Python Code)

Max Activating Token Index: 381

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0467. Min Act: -0.0004

Data Index: 1374846 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1488182 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1553955 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1419410 (Python Code)

Max Activating Token Index: 10

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1549011 (Python Code)

Max Activating Token Index: 650

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1534295 (Python Code)

Max Activating Token Index: 791

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1448857 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1402882 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1496309 (Python Code)

Max Activating Token Index: 111

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1475591 (Python Code)

Max Activating Token Index: 393

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1624703 (Python Code)

Max Activating Token Index: 745

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1524026 (Python Code)

Max Activating Token Index: 181

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0407. Min Act: -0.0004

Data Index: 1380401 (Python Code)

Max Activating Token Index: 37

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1364216 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0429. Min Act: -0.0003

Data Index: 1626172 (Python Code)

Max Activating Token Index: 445

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1440917 (Python Code)

Max Activating Token Index: 235

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1546413 (Python Code)

Max Activating Token Index: 114