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

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

Neuron 2568 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.8006. Min Act: -0.0001

Data Index: 1555011 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.4613. Min Act: -0.0001

Data Index: 1421838 (Python Code)

Max Activating Token Index: 417

Text #2

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.2121. Min Act: -0.0001

Data Index: 1430486 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.5484. Min Act: -0.0000

Data Index: 1604824 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.7715. Min Act: -0.0001

Data Index: 1597048 (Python Code)

Max Activating Token Index: 743

Text #5

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.0624. Min Act: -0.0001

Data Index: 1513071 (Python Code)

Max Activating Token Index: 872

Text #6

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.0424. Min Act: -0.0001

Data Index: 1582202 (Python Code)

Max Activating Token Index: 745

Text #7

Max Range: 5.8006. Min Range: -5.8006

Max Act: 5.0318. Min Act: -0.0001

Data Index: 1478848 (Python Code)

Max Activating Token Index: 394

Text #8

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.8105. Min Act: -0.0001

Data Index: 1551570 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.7757. Min Act: -0.0001

Data Index: 1633643 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.7614. Min Act: -0.0001

Data Index: 1404187 (Python Code)

Max Activating Token Index: 944

Text #11

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.8722. Min Act: -0.0001

Data Index: 1639513 (Python Code)

Max Activating Token Index: 283

Text #12

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.6707. Min Act: -0.0001

Data Index: 1599602 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.6171. Min Act: -0.0001

Data Index: 1433359 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.9771. Min Act: -0.0001

Data Index: 1559895 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.5926. Min Act: -0.0001

Data Index: 1456181 (Python Code)

Max Activating Token Index: 435

Text #16

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.7363. Min Act: -0.0001

Data Index: 1430765 (Python Code)

Max Activating Token Index: 1000

Text #17

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.5626. Min Act: -0.0001

Data Index: 1431880 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.5237. Min Act: -0.0001

Data Index: 1479757 (Python Code)

Max Activating Token Index: 949

Text #19

Max Range: 5.8006. Min Range: -5.8006

Max Act: 4.7059. Min Act: -0.0001

Data Index: 1453644 (Python Code)

Max Activating Token Index: 436