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

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

Neuron 2959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1607102 (Python Code)

Max Activating Token Index: 349

Text #1

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.4622. Min Act: -0.0000

Data Index: 1472480 (Python Code)

Max Activating Token Index: 307

Text #2

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.3836. Min Act: -0.0000

Data Index: 1616909 (Python Code)

Max Activating Token Index: 675

Text #3

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.3602. Min Act: -0.0000

Data Index: 1492476 (Python Code)

Max Activating Token Index: 483

Text #4

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.3071. Min Act: -0.0000

Data Index: 1587025 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0911. Min Act: -0.0000

Data Index: 1452401 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.1566. Min Act: -0.0000

Data Index: 1585163 (Python Code)

Max Activating Token Index: 151

Text #7

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.1406. Min Act: -0.0000

Data Index: 1609683 (Python Code)

Max Activating Token Index: 215

Text #8

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.1209. Min Act: -0.0000

Data Index: 1379642 (Python Code)

Max Activating Token Index: 491

Text #9

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1617596 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0763. Min Act: -0.0000

Data Index: 1519024 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0605. Min Act: -0.0000

Data Index: 1553359 (Python Code)

Max Activating Token Index: 559

Text #12

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0467. Min Act: -0.0000

Data Index: 1513370 (Python Code)

Max Activating Token Index: 560

Text #13

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1458635 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.8827. Min Act: -0.0000

Data Index: 1568931 (Python Code)

Max Activating Token Index: 350

Text #15

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0225. Min Act: -0.0000

Data Index: 1469817 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1387060 (Python Code)

Max Activating Token Index: 273

Text #17

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.9883. Min Act: -0.0000

Data Index: 1497540 (Python Code)

Max Activating Token Index: 732

Text #18

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.7693. Min Act: -0.0001

Data Index: 1416689 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.7342. Min Act: -0.0000

Data Index: 1564191 (Python Code)

Max Activating Token Index: 70