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

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

Neuron 485 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6266. Min Range: -5.6266

Max Act: 5.6266. Min Act: -0.0000

Data Index: 1540351 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.1629. Min Act: -0.0000

Data Index: 1394500 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 5.6266. Min Range: -5.6266

Max Act: 4.1642. Min Act: -0.0000

Data Index: 1404839 (Python Code)

Max Activating Token Index: 780

Text #3

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.5813. Min Act: -0.0000

Data Index: 1601096 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.7676. Min Act: -0.0000

Data Index: 1446138 (Python Code)

Max Activating Token Index: 813

Text #5

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.8107. Min Act: -0.0000

Data Index: 1500228 (Python Code)

Max Activating Token Index: 547

Text #6

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.5662. Min Act: -0.0000

Data Index: 1448118 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.3547. Min Act: -0.0000

Data Index: 1458206 (Python Code)

Max Activating Token Index: 534

Text #8

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.4729. Min Act: -0.0000

Data Index: 1562501 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.1547. Min Act: -0.0000

Data Index: 1490596 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.3971. Min Act: -0.0000

Data Index: 1436676 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.5159. Min Act: -0.0000

Data Index: 1465031 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.3081. Min Act: -0.0000

Data Index: 1639289 (Python Code)

Max Activating Token Index: 800

Text #13

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.1579. Min Act: -0.0000

Data Index: 1567841 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.2631. Min Act: -0.0000

Data Index: 1654194 (Python Code)

Max Activating Token Index: 827

Text #15

Max Range: 5.6266. Min Range: -5.6266

Max Act: 2.8109. Min Act: -0.0000

Data Index: 1640323 (Python Code)

Max Activating Token Index: 666

Text #16

Max Range: 5.6266. Min Range: -5.6266

Max Act: 2.7301. Min Act: -0.0000

Data Index: 1381547 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.2233. Min Act: -0.0000

Data Index: 1494553 (Python Code)

Max Activating Token Index: 602

Text #18

Max Range: 5.6266. Min Range: -5.6266

Max Act: 2.9423. Min Act: -0.0000

Data Index: 1425300 (Python Code)

Max Activating Token Index: 593

Text #19

Max Range: 5.6266. Min Range: -5.6266

Max Act: 3.3353. Min Act: -0.0000

Data Index: 1407775 (Python Code)

Max Activating Token Index: 783