Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1564778 (Python Code)

Max Activating Token Index: 462

Text #1

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1566231 (Python Code)

Max Activating Token Index: 837

Text #2

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7880. Min Act: -0.0001

Data Index: 1549292 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7478. Min Act: -0.0001

Data Index: 1628821 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7445. Min Act: -0.0001

Data Index: 1564835 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6504. Min Act: -0.0001

Data Index: 1496261 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1394729 (Python Code)

Max Activating Token Index: 661

Text #7

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1624986 (Python Code)

Max Activating Token Index: 775

Text #8

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1532332 (Python Code)

Max Activating Token Index: 757

Text #9

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6693. Min Act: -0.0001

Data Index: 1393098 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6278. Min Act: -0.0001

Data Index: 1640932 (Python Code)

Max Activating Token Index: 411

Text #11

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6455. Min Act: -0.0001

Data Index: 1494723 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6045. Min Act: -0.0001

Data Index: 1389903 (Python Code)

Max Activating Token Index: 282

Text #13

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1623896 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6338. Min Act: -0.0001

Data Index: 1580686 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1509572 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6471. Min Act: -0.0001

Data Index: 1483380 (Python Code)

Max Activating Token Index: 89

Text #17

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6266. Min Act: -0.0000

Data Index: 1571272 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6071. Min Act: -0.0001

Data Index: 1526927 (Python Code)

Max Activating Token Index: 899

Text #19

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1458847 (Python Code)

Max Activating Token Index: 607