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

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

Neuron 826 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0002

Data Index: 1119687 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1200. Min Act: -0.0002

Data Index: 298237 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1249. Min Act: -0.0002

Data Index: 276968 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1154. Min Act: -0.0002

Data Index: 697928 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1099698 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1178. Min Act: -0.0002

Data Index: 899236 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1163534 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1290210 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1062629 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1071. Min Act: -0.0002

Data Index: 592057 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1071. Min Act: -0.0002

Data Index: 592289 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1035. Min Act: -0.0002

Data Index: 681831 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1529777 (Python Code)

Max Activating Token Index: 53

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1358195 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1551776 (Python Code)

Max Activating Token Index: 645

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1502605 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1007. Min Act: -0.0002

Data Index: 40632 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0932. Min Act: -0.0002

Data Index: 391477 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0992. Min Act: -0.0002

Data Index: 850358 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1008509 (C4 (Web Text))

Max Activating Token Index: 497