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

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

Neuron 506 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1651. Min Act: -0.0000

Data Index: 863928 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1724. Min Act: -0.0000

Data Index: 645778 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1220886 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1308. Min Act: -0.0000

Data Index: 833969 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1291. Min Act: -0.0000

Data Index: 244344 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1291. Min Act: -0.0000

Data Index: 835449 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1177206 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1218. Min Act: -0.0000

Data Index: 229598 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1213414 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1111. Min Act: -0.0000

Data Index: 628429 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1178. Min Act: -0.0000

Data Index: 749696 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1102. Min Act: -0.0000

Data Index: 903710 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1226609 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1181030 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1190. Min Act: -0.0000

Data Index: 343823 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1118. Min Act: -0.0000

Data Index: 298915 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1042. Min Act: -0.0000

Data Index: 492851 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1112414 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1634 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.1724. Min Range: -0.1724

Max Act: 0.0993. Min Act: -0.0000

Data Index: 51560 (C4 (Web Text))

Max Activating Token Index: 922