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

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

Neuron 4617 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: 2.3544. Min Range: -2.3544

Max Act: 2.2645. Min Act: -0.0000

Data Index: 1471431 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.3544. Min Act: -0.0000

Data Index: 1551977 (Python Code)

Max Activating Token Index: 765

Text #2

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.3432. Min Act: -0.0000

Data Index: 1435343 (Python Code)

Max Activating Token Index: 541

Text #3

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.3477. Min Act: -0.0000

Data Index: 1546121 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1509118 (Python Code)

Max Activating Token Index: 45

Text #5

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1754. Min Act: -0.0000

Data Index: 1470752 (Python Code)

Max Activating Token Index: 955

Text #6

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.9536. Min Act: -0.0000

Data Index: 1463548 (Python Code)

Max Activating Token Index: 655

Text #7

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1661. Min Act: -0.0000

Data Index: 1443052 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1113. Min Act: -0.0000

Data Index: 1391025 (Python Code)

Max Activating Token Index: 223

Text #9

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.0678. Min Act: -0.0000

Data Index: 1639017 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.9627. Min Act: -0.0000

Data Index: 1382182 (Python Code)

Max Activating Token Index: 967

Text #11

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.0260. Min Act: -0.0000

Data Index: 1401780 (Python Code)

Max Activating Token Index: 805

Text #12

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1314. Min Act: -0.0001

Data Index: 1546542 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.0146. Min Act: -0.0000

Data Index: 1654636 (Python Code)

Max Activating Token Index: 785

Text #14

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.0111. Min Act: -0.0000

Data Index: 1566289 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.9048. Min Act: -0.0000

Data Index: 1533781 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 2.3544. Min Range: -2.3544

Max Act: 2.1096. Min Act: -0.0000

Data Index: 1613629 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.9837. Min Act: -0.0000

Data Index: 1453436 (Python Code)

Max Activating Token Index: 311

Text #18

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.8765. Min Act: -0.0000

Data Index: 1420241 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 2.3544. Min Range: -2.3544

Max Act: 1.8806. Min Act: -0.0000

Data Index: 1511142 (Python Code)

Max Activating Token Index: 7