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

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

Neuron 4482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1487381 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1496221 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1513443 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1466210 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1492212 (Python Code)

Max Activating Token Index: 69

Text #5

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1381647 (Python Code)

Max Activating Token Index: 329

Text #6

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1476424 (Python Code)

Max Activating Token Index: 56

Text #7

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1369954 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1576557 (Python Code)

Max Activating Token Index: 714

Text #9

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1606474 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1383539 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1448734 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1437644 (Python Code)

Max Activating Token Index: 291

Text #13

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1645357 (Python Code)

Max Activating Token Index: 520

Text #14

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1413434 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1576061 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1419488 (Python Code)

Max Activating Token Index: 533

Text #17

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1512802 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7234. Min Act: -0.0000

Data Index: 1564013 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 0.8334. Min Range: -0.8334

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1370732 (Python Code)

Max Activating Token Index: 50