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

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

Neuron 2003 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: 0.3221. Min Range: -0.3221

Max Act: 0.3221. Min Act: -0.0000

Data Index: 419386 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1314977 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2311. Min Act: -0.0000

Data Index: 106871 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2433. Min Act: -0.0000

Data Index: 274942 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2276. Min Act: -0.0000

Data Index: 737936 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1170931 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2240. Min Act: -0.0000

Data Index: 862363 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2049. Min Act: -0.0000

Data Index: 523246 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1015011 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1867. Min Act: -0.0000

Data Index: 317439 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1143148 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1779. Min Act: -0.0000

Data Index: 681801 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1706. Min Act: -0.0000

Data Index: 437300 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1768. Min Act: -0.0000

Data Index: 899456 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1870. Min Act: -0.0000

Data Index: 505038 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1816. Min Act: -0.0000

Data Index: 673207 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1272515 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1027261 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1257637 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.1650. Min Act: -0.0000

Data Index: 478987 (C4 (Web Text))

Max Activating Token Index: 307