Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5943 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1178644 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0000

Data Index: 882771 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1405. Min Act: -0.0000

Data Index: 177687 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1337. Min Act: -0.0001

Data Index: 118551 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1351. Min Act: -0.0000

Data Index: 902381 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1281. Min Act: -0.0001

Data Index: 101580 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1232657 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1181. Min Act: -0.0000

Data Index: 609409 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1187. Min Act: -0.0000

Data Index: 150367 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1075. Min Act: -0.0000

Data Index: 35838 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1221. Min Act: -0.0000

Data Index: 177710 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1176. Min Act: -0.0000

Data Index: 648674 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1075303 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1313. Min Act: -0.0001

Data Index: 296565 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1150. Min Act: -0.0001

Data Index: 919447 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1213. Min Act: -0.0000

Data Index: 1123452 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1143. Min Act: -0.0001

Data Index: 763054 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1264340 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1106. Min Act: -0.0000

Data Index: 611914 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1062. Min Act: -0.0001

Data Index: 26800 (C4 (Web Text))

Max Activating Token Index: 842