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

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

Neuron 2872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1452579 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1556209 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1598453 (Python Code)

Max Activating Token Index: 540

Text #3

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1435916 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7832. Min Act: -0.0001

Data Index: 1502253 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1619194 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1610185 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1586013 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1393924 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1436189 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7346. Min Act: -0.0001

Data Index: 1384484 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1391401 (Python Code)

Max Activating Token Index: 173

Text #12

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1416911 (Python Code)

Max Activating Token Index: 918

Text #13

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1483806 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1471719 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1580946 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7462. Min Act: -0.0001

Data Index: 1397039 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7389. Min Act: -0.0001

Data Index: 1443013 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1533449 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1568520 (Python Code)

Max Activating Token Index: 242