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

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

Neuron 619 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1618. Min Act: -0.0001

Data Index: 639033 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1482. Min Act: -0.0001

Data Index: 6241 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1264770 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1410. Min Act: -0.0001

Data Index: 478566 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1365. Min Act: -0.0001

Data Index: 703113 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1394. Min Act: -0.0001

Data Index: 247881 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1403. Min Act: -0.0001

Data Index: 807063 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1246. Min Act: -0.0001

Data Index: 902359 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1302. Min Act: -0.0001

Data Index: 626511 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1260. Min Act: -0.0001

Data Index: 561953 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1035996 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1240. Min Act: -0.0001

Data Index: 163081 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1223. Min Act: -0.0001

Data Index: 819171 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1162. Min Act: -0.0001

Data Index: 851567 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1118. Min Act: -0.0001

Data Index: 388496 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1272. Min Act: -0.0001

Data Index: 562319 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1046002 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1285. Min Act: -0.0001

Data Index: 342751 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1148. Min Act: -0.0001

Data Index: 104038 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1618. Min Range: -0.1618

Max Act: 0.1123. Min Act: -0.0001

Data Index: 906740 (C4 (Web Text))

Max Activating Token Index: 146