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

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

Neuron 3522 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1346. Min Act: -0.0001

Data Index: 758054 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1067049 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1278. Min Act: -0.0001

Data Index: 186782 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1227. Min Act: -0.0001

Data Index: 972243 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1237. Min Act: -0.0001

Data Index: 593986 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1242. Min Act: -0.0001

Data Index: 39110 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1169. Min Act: -0.0001

Data Index: 616133 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1166. Min Act: -0.0001

Data Index: 656138 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1167164 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1204. Min Act: -0.0001

Data Index: 879729 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1117. Min Act: -0.0001

Data Index: 620107 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1066. Min Act: -0.0001

Data Index: 155375 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1097. Min Act: -0.0001

Data Index: 720250 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1231785 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1042. Min Act: -0.0001

Data Index: 860072 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1182333 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1083. Min Act: -0.0001

Data Index: 431584 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1315083 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1042588 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.1346. Min Range: -0.1346

Max Act: 0.1019. Min Act: -0.0001

Data Index: 638030 (C4 (Web Text))

Max Activating Token Index: 568