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

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

Neuron 1106 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: 1.0990. Min Range: -1.0990

Max Act: 1.0990. Min Act: -0.0000

Data Index: 1540567 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1497465 (Python Code)

Max Activating Token Index: 831

Text #2

Max Range: 1.0990. Min Range: -1.0990

Max Act: 1.0707. Min Act: -0.0000

Data Index: 1471916 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 1.0990. Min Range: -1.0990

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1533567 (Python Code)

Max Activating Token Index: 244

Text #4

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1450396 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1446465 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1583279 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1373450 (Python Code)

Max Activating Token Index: 47

Text #8

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1636553 (Python Code)

Max Activating Token Index: 118

Text #9

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1403263 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1444603 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1654561 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1397508 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1518377 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1374628 (Python Code)

Max Activating Token Index: 235

Text #15

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1439354 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1442427 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1647835 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.8243. Min Act: -0.0001

Data Index: 1646544 (Python Code)

Max Activating Token Index: 44

Text #19

Max Range: 1.0990. Min Range: -1.0990

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1618655 (Python Code)

Max Activating Token Index: 31