Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1573 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.8848. Min Range: -3.8848

Max Act: 3.8848. Min Act: -0.0001

Data Index: 813294 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 3.8848. Min Range: -3.8848

Max Act: 2.5625. Min Act: -0.0002

Data Index: 604060 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 3.8848. Min Range: -3.8848

Max Act: 2.3164. Min Act: -0.0002

Data Index: 282178 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.8848. Min Range: -3.8848

Max Act: 2.1678. Min Act: -0.0002

Data Index: 1086662 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 3.8848. Min Range: -3.8848

Max Act: 2.2104. Min Act: -0.0002

Data Index: 1251179 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.8959. Min Act: -0.0002

Data Index: 42390 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.3035. Min Act: -0.0001

Data Index: 186695 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.4104. Min Act: -0.0002

Data Index: 1110962 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.3271. Min Act: -0.0001

Data Index: 108278 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.3194. Min Act: -0.0001

Data Index: 758124 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.1793. Min Act: -0.0001

Data Index: 618672 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.2621. Min Act: -0.0001

Data Index: 1130802 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.0044. Min Act: -0.0002

Data Index: 419592 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.1196. Min Act: -0.0001

Data Index: 942034 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.1036. Min Act: -0.0002

Data Index: 437290 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.0926. Min Act: -0.0001

Data Index: 45127 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.2483. Min Act: -0.0001

Data Index: 1203494 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.2142. Min Act: -0.0001

Data Index: 352280 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.0303. Min Act: -0.0001

Data Index: 571314 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 3.8848. Min Range: -3.8848

Max Act: 1.0676. Min Act: -0.0001

Data Index: 451132 (C4 (Web Text))

Max Activating Token Index: 360