Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1189. Min Act: -0.0001

Data Index: 862789 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1172. Min Act: -0.0001

Data Index: 527278 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1195. Min Act: -0.0001

Data Index: 380905 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1144. Min Act: -0.0001

Data Index: 600101 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1146. Min Act: -0.0001

Data Index: 184674 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1203836 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1124. Min Act: -0.0001

Data Index: 44460 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1141142 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1216420 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1046. Min Act: -0.0001

Data Index: 503640 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1033093 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1042. Min Act: -0.0001

Data Index: 194163 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1065594 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1034. Min Act: -0.0001

Data Index: 384572 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0961. Min Act: -0.0001

Data Index: 977199 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1029. Min Act: -0.0001

Data Index: 987845 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1103. Min Act: -0.0001

Data Index: 674538 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.0981. Min Act: -0.0001

Data Index: 383485 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1047. Min Act: -0.0001

Data Index: 944826 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.1195. Min Range: -0.1195

Max Act: 0.1057. Min Act: -0.0001

Data Index: 709618 (C4 (Web Text))

Max Activating Token Index: 602