Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 87 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1380132 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1576082 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3837. Min Act: -0.0001

Data Index: 1393170 (Python Code)

Max Activating Token Index: 657

Text #3

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1619805 (Python Code)

Max Activating Token Index: 42

Text #4

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3535. Min Act: -0.0001

Data Index: 1438522 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1597910 (Python Code)

Max Activating Token Index: 501

Text #6

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1410966 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3602. Min Act: -0.0001

Data Index: 1540352 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1391534 (Python Code)

Max Activating Token Index: 522

Text #9

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3509. Min Act: -0.0001

Data Index: 1471733 (Python Code)

Max Activating Token Index: 962

Text #10

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3602. Min Act: -0.0001

Data Index: 1613486 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1564269 (Python Code)

Max Activating Token Index: 842

Text #12

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3278. Min Act: -0.0001

Data Index: 1382139 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1541413 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3338. Min Act: -0.0001

Data Index: 1440712 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1542152 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1478363 (Python Code)

Max Activating Token Index: 79

Text #17

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1647503 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1560712 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.4676. Min Range: -0.4676

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1611178 (Python Code)

Max Activating Token Index: 372