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

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

Neuron 5987 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.9565. Min Act: -0.0000

Data Index: 1364217 (Python Code)

Max Activating Token Index: 708

Text #1

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.8483. Min Act: -0.0000

Data Index: 1381829 (Python Code)

Max Activating Token Index: 236

Text #2

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1633887 (Python Code)

Max Activating Token Index: 886

Text #3

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6707. Min Act: -0.0000

Data Index: 1592784 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.7067. Min Act: -0.0000

Data Index: 1485455 (Python Code)

Max Activating Token Index: 489

Text #5

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1565503 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.5891. Min Act: -0.0000

Data Index: 1430602 (Python Code)

Max Activating Token Index: 700

Text #7

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.7526. Min Act: -0.0000

Data Index: 1627362 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6535. Min Act: -0.0000

Data Index: 1552996 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1616030 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6364. Min Act: -0.0000

Data Index: 1593780 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6363. Min Act: -0.0001

Data Index: 1588847 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6368. Min Act: -0.0000

Data Index: 1592535 (Python Code)

Max Activating Token Index: 180

Text #13

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1591657 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6014. Min Act: -0.0000

Data Index: 1366643 (Python Code)

Max Activating Token Index: 894

Text #15

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.5906. Min Act: -0.0000

Data Index: 1572337 (Python Code)

Max Activating Token Index: 387

Text #16

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1596712 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1385364 (Python Code)

Max Activating Token Index: 114

Text #18

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1593604 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 1.9565. Min Range: -1.9565

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1479611 (Python Code)

Max Activating Token Index: 701