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

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

Neuron 3953 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.5974. Min Act: -0.0000

Data Index: 1607593 (Python Code)

Max Activating Token Index: 934

Text #1

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1600344 (Python Code)

Max Activating Token Index: 357

Text #2

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1475193 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1436434 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1569176 (Python Code)

Max Activating Token Index: 449

Text #5

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2099. Min Act: -0.0000

Data Index: 1514279 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1534150 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1373324 (Python Code)

Max Activating Token Index: 1014

Text #8

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1584751 (Python Code)

Max Activating Token Index: 437

Text #9

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1464010 (Python Code)

Max Activating Token Index: 525

Text #10

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.0605. Min Act: -0.0000

Data Index: 1360514 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 1.5974. Min Range: -1.5974

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1497832 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1555674 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1397518 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1410480 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1585422 (Python Code)

Max Activating Token Index: 50

Text #16

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1607281 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1645278 (Python Code)

Max Activating Token Index: 49

Text #18

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1527365 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 1.5974. Min Range: -1.5974

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1570710 (Python Code)

Max Activating Token Index: 630