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

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

Neuron 3765 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1650. Min Act: -0.0001

Data Index: 372859 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1559. Min Act: -0.0001

Data Index: 950114 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1240586 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1487. Min Act: -0.0001

Data Index: 809583 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1314. Min Act: -0.0001

Data Index: 946928 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1248. Min Act: -0.0001

Data Index: 344854 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1223. Min Act: -0.0001

Data Index: 430275 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1086653 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1290524 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1191. Min Act: -0.0001

Data Index: 634204 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1202. Min Act: -0.0001

Data Index: 386011 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1167. Min Act: -0.0001

Data Index: 66790 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1087953 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1064. Min Act: -0.0001

Data Index: 304428 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1101. Min Act: -0.0001

Data Index: 205486 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1175. Min Act: -0.0001

Data Index: 668305 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1179. Min Act: -0.0001

Data Index: 969333 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1117. Min Act: -0.0001

Data Index: 274908 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1139. Min Act: -0.0001

Data Index: 60624 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 0.1650. Min Range: -0.1650

Max Act: 0.1125. Min Act: -0.0001

Data Index: 108482 (C4 (Web Text))

Max Activating Token Index: 307