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

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

Neuron 5292 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0602. Min Range: -1.0602

Max Act: 1.0602. Min Act: -0.0002

Data Index: 1494048 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 1.0602. Min Range: -1.0602

Max Act: 1.0133. Min Act: -0.0002

Data Index: 1402599 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9509. Min Act: -0.0002

Data Index: 1558328 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9441. Min Act: -0.0002

Data Index: 1542830 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9708. Min Act: -0.0002

Data Index: 1365516 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9444. Min Act: -0.0002

Data Index: 1555711 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9654. Min Act: -0.0002

Data Index: 1370078 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.9165. Min Act: -0.0002

Data Index: 1517140 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8667. Min Act: -0.0002

Data Index: 1447098 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8904. Min Act: -0.0002

Data Index: 1553301 (Python Code)

Max Activating Token Index: 909

Text #10

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7930. Min Act: -0.0002

Data Index: 1419030 (Python Code)

Max Activating Token Index: 669

Text #11

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8239. Min Act: -0.0002

Data Index: 1380963 (Python Code)

Max Activating Token Index: 329

Text #12

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7905. Min Act: -0.0002

Data Index: 1480725 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7822. Min Act: -0.0002

Data Index: 1483627 (Python Code)

Max Activating Token Index: 258

Text #14

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7751. Min Act: -0.0002

Data Index: 1620671 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8215. Min Act: -0.0002

Data Index: 1370124 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8112. Min Act: -0.0002

Data Index: 1454604 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7823. Min Act: -0.0002

Data Index: 1452780 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7465. Min Act: -0.0002

Data Index: 1401551 (Python Code)

Max Activating Token Index: 856

Text #19

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7624. Min Act: -0.0002

Data Index: 1486802 (Python Code)

Max Activating Token Index: 650