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

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

Neuron 723 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: 1.4923. Min Range: -1.4923

Max Act: 1.4923. Min Act: -0.0000

Data Index: 1475538 (Python Code)

Max Activating Token Index: 862

Text #1

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1572532 (Python Code)

Max Activating Token Index: 634

Text #2

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1444913 (Python Code)

Max Activating Token Index: 164

Text #3

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1499729 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0005. Min Act: -0.0000

Data Index: 1648480 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1215279 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1614510 (Python Code)

Max Activating Token Index: 602

Text #7

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1446034 (Python Code)

Max Activating Token Index: 907

Text #8

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1433422 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9216. Min Act: -0.0000

Data Index: 519106 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9199. Min Act: -0.0001

Data Index: 1486802 (Python Code)

Max Activating Token Index: 939

Text #11

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1429380 (Python Code)

Max Activating Token Index: 652

Text #12

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1432069 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1506436 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1653491 (Python Code)

Max Activating Token Index: 841

Text #15

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.8543. Min Act: -0.0000

Data Index: 845369 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1405089 (Python Code)

Max Activating Token Index: 578

Text #17

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1462285 (Python Code)

Max Activating Token Index: 915

Text #18

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1083106 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1453810 (Python Code)

Max Activating Token Index: 851