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

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

Neuron 740 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8623. Min Range: -2.8623

Max Act: 2.8623. Min Act: -0.0000

Data Index: 1491511 (Python Code)

Max Activating Token Index: 803

Text #1

Max Range: 2.8623. Min Range: -2.8623

Max Act: 2.5043. Min Act: -0.0000

Data Index: 1376927 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 2.8623. Min Range: -2.8623

Max Act: 2.0226. Min Act: -0.0000

Data Index: 1568697 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.9617. Min Act: -0.0000

Data Index: 1569344 (Python Code)

Max Activating Token Index: 90

Text #4

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.8173. Min Act: -0.0000

Data Index: 1365969 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.8666. Min Act: -0.0000

Data Index: 1560035 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.8665. Min Act: -0.0000

Data Index: 1619719 (Python Code)

Max Activating Token Index: 154

Text #7

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1545880 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.7474. Min Act: -0.0000

Data Index: 1415036 (Python Code)

Max Activating Token Index: 223

Text #9

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1507198 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1600485 (Python Code)

Max Activating Token Index: 462

Text #11

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.6766. Min Act: -0.0000

Data Index: 1511328 (Python Code)

Max Activating Token Index: 346

Text #12

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1651628 (Python Code)

Max Activating Token Index: 517

Text #13

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.5994. Min Act: -0.0000

Data Index: 1602929 (Python Code)

Max Activating Token Index: 873

Text #14

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1602574 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.6657. Min Act: -0.0000

Data Index: 1570153 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1560032 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.5423. Min Act: -0.0000

Data Index: 1610822 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1574340 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.8623. Min Range: -2.8623

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1405285 (Python Code)

Max Activating Token Index: 886