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

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

Neuron 1689 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: 0.9880. Min Range: -0.9880

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1631378 (Python Code)

Max Activating Token Index: 945

Text #1

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1458597 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1656524 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1538126 (Python Code)

Max Activating Token Index: 174

Text #4

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1647402 (Python Code)

Max Activating Token Index: 180

Text #5

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1446136 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1552499 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1511769 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1433285 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1484838 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1492388 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1477273 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1604445 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1381232 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1362411 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1585523 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1417708 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1622517 (Python Code)

Max Activating Token Index: 706

Text #18

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1643115 (Python Code)

Max Activating Token Index: 522

Text #19

Max Range: 0.9880. Min Range: -0.9880

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1480643 (Python Code)

Max Activating Token Index: 20