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

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

Neuron 1636 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1559662 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1601406 (Python Code)

Max Activating Token Index: 95

Text #2

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1591481 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1571259 (Python Code)

Max Activating Token Index: 824

Text #4

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1506702 (Python Code)

Max Activating Token Index: 677

Text #5

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1509132 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1576778 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1594069 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1412263 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1553819 (Python Code)

Max Activating Token Index: 213

Text #10

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1636543 (Python Code)

Max Activating Token Index: 755

Text #11

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1584182 (Python Code)

Max Activating Token Index: 837

Text #12

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1386414 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1418936 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1543853 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1413636 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1527591 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1528522 (Python Code)

Max Activating Token Index: 459

Text #18

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1369374 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1548892 (Python Code)

Max Activating Token Index: 1018