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

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

Neuron 115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1526. Min Act: -0.0001

Data Index: 984214 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1303. Min Act: -0.0001

Data Index: 476788 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1378. Min Act: -0.0000

Data Index: 233912 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1332. Min Act: -0.0001

Data Index: 554793 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1343. Min Act: -0.0001

Data Index: 477282 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1416. Min Act: -0.0000

Data Index: 264824 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1295705 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1249. Min Act: -0.0000

Data Index: 189520 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1258. Min Act: -0.0000

Data Index: 52564 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1344. Min Act: -0.0001

Data Index: 650857 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1156625 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1141338 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1040. Min Act: -0.0001

Data Index: 52064 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1275. Min Act: -0.0001

Data Index: 993940 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1101. Min Act: -0.0001

Data Index: 555829 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1262. Min Act: -0.0001

Data Index: 603934 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1298. Min Act: -0.0001

Data Index: 1321219 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1292881 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1167. Min Act: -0.0000

Data Index: 225688 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1107. Min Act: -0.0000

Data Index: 61649 (C4 (Web Text))

Max Activating Token Index: 430