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

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

Neuron 320 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: 0.1965. Min Range: -0.1965

Max Act: 0.1965. Min Act: -0.0000

Data Index: 780907 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1302506 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1049800 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1673. Min Act: -0.0000

Data Index: 782713 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1136233 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1840. Min Act: -0.0000

Data Index: 106498 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1715. Min Act: -0.0000

Data Index: 337032 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1720. Min Act: -0.0000

Data Index: 172886 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1288254 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1159541 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1581. Min Act: -0.0000

Data Index: 964287 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1744. Min Act: -0.0000

Data Index: 990998 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1330249 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1620. Min Act: -0.0000

Data Index: 819497 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1294613 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1657. Min Act: -0.0000

Data Index: 771196 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1050886 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1639. Min Act: -0.0000

Data Index: 79443 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1495. Min Act: -0.0000

Data Index: 767340 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1572. Min Act: -0.0000

Data Index: 843829 (C4 (Web Text))

Max Activating Token Index: 545