Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5180 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0071. Min Act: -0.0001

Data Index: 1504877 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0057. Min Act: -0.0001

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1455071 (Python Code)

Max Activating Token Index: 665

Text #3

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0047. Min Act: -0.0001

Data Index: 1416090 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0049. Min Act: -0.0001

Data Index: 1632866 (Python Code)

Max Activating Token Index: 640

Text #5

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1506171 (Python Code)

Max Activating Token Index: 611

Text #6

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0044. Min Act: -0.0001

Data Index: 1437233 (Python Code)

Max Activating Token Index: 279

Text #7

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0047. Min Act: -0.0001

Data Index: 1603660 (Python Code)

Max Activating Token Index: 901

Text #8

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0037. Min Act: -0.0001

Data Index: 1621468 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0038. Min Act: -0.0001

Data Index: 1557998 (Python Code)

Max Activating Token Index: 490

Text #10

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0031. Min Act: -0.0001

Data Index: 1423605 (Python Code)

Max Activating Token Index: 72

Text #11

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0031. Min Act: -0.0001

Data Index: 1531321 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0029. Min Act: -0.0001

Data Index: 1381178 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0024. Min Act: -0.0001

Data Index: 1475633 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0025. Min Act: -0.0001

Data Index: 1422095 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0028. Min Act: -0.0001

Data Index: 1442844 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0026. Min Act: -0.0001

Data Index: 1570350 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0026. Min Act: -0.0001

Data Index: 1602617 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0026. Min Act: -0.0001

Data Index: 1486556 (Python Code)

Max Activating Token Index: 463

Text #19

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0026. Min Act: -0.0001

Data Index: 1484726 (Python Code)

Max Activating Token Index: 7