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

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

Neuron 3578 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: 4.6351. Min Range: -4.6351

Max Act: 4.6351. Min Act: -0.0000

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 4.6351. Min Range: -4.6351

Max Act: 4.2338. Min Act: -0.0000

Data Index: 314420 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 4.6351. Min Range: -4.6351

Max Act: 4.3816. Min Act: -0.0000

Data Index: 891787 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 4.6351. Min Range: -4.6351

Max Act: 4.2844. Min Act: -0.0000

Data Index: 1046931 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 4.6351. Min Range: -4.6351

Max Act: 3.5316. Min Act: -0.0000

Data Index: 452986 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 4.6351. Min Range: -4.6351

Max Act: 3.6046. Min Act: -0.0000

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 4.6351. Min Range: -4.6351

Max Act: 3.6303. Min Act: -0.0000

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 4.6351. Min Range: -4.6351

Max Act: 3.3530. Min Act: -0.0000

Data Index: 1317592 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 4.6351. Min Range: -4.6351

Max Act: 3.1612. Min Act: -0.0000

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.9438. Min Act: -0.0000

Data Index: 808695 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.9067. Min Act: -0.0000

Data Index: 1314142 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.7720. Min Act: -0.0000

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.7091. Min Act: -0.0000

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.6867. Min Act: -0.0000

Data Index: 1076561 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.6974. Min Act: -0.0000

Data Index: 1296059 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.5758. Min Act: -0.0000

Data Index: 283759 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.5232. Min Act: -0.0000

Data Index: 956841 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.4987. Min Act: -0.0000

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.4668. Min Act: -0.0000

Data Index: 749778 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 4.6351. Min Range: -4.6351

Max Act: 2.6024. Min Act: -0.0000

Data Index: 1330911 (C4 (Web Text))

Max Activating Token Index: 94