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

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

Neuron 871 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: 0.1704. Min Range: -0.1704

Max Act: 0.1704. Min Act: -0.0001

Data Index: 27472 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1455. Min Act: -0.0001

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1232. Min Act: -0.0001

Data Index: 627192 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1227. Min Act: -0.0001

Data Index: 848027 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1206. Min Act: -0.0001

Data Index: 866853 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1201. Min Act: -0.0001

Data Index: 97069 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1286. Min Act: -0.0002

Data Index: 333788 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1110295 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1357355 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1273400 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1214. Min Act: -0.0002

Data Index: 333125 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1208. Min Act: -0.0001

Data Index: 352267 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1225. Min Act: -0.0001

Data Index: 89317 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1306949 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1111. Min Act: -0.0001

Data Index: 740434 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1170. Min Act: -0.0001

Data Index: 516434 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1086. Min Act: -0.0001

Data Index: 238427 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1245. Min Act: -0.0001

Data Index: 707488 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.1704. Min Range: -0.1704

Max Act: 0.1200. Min Act: -0.0001

Data Index: 880952 (C4 (Web Text))

Max Activating Token Index: 742