Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1398. Min Act: -0.0002

Data Index: 570940 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1438. Min Act: -0.0002

Data Index: 1023613 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1239. Min Act: -0.0002

Data Index: 429306 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1182. Min Act: -0.0002

Data Index: 131908 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1312672 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1132. Min Act: -0.0001

Data Index: 287961 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1213. Min Act: -0.0001

Data Index: 538717 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1114. Min Act: -0.0001

Data Index: 358590 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1100. Min Act: -0.0002

Data Index: 887022 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1228. Min Act: -0.0002

Data Index: 1093222 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1106. Min Act: -0.0002

Data Index: 437843 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1113. Min Act: -0.0002

Data Index: 64527 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1056. Min Act: -0.0002

Data Index: 80067 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1182. Min Act: -0.0001

Data Index: 212175 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1043625 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1092. Min Act: -0.0002

Data Index: 576838 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1064. Min Act: -0.0002

Data Index: 171425 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1049. Min Act: -0.0001

Data Index: 61467 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1043. Min Act: -0.0002

Data Index: 563058 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1342354 (C4 (Web Text))

Max Activating Token Index: 937