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

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

Neuron 2893 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1212872 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1137. Min Act: -0.0001

Data Index: 982477 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1233. Min Act: -0.0001

Data Index: 892146 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1139728 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1188. Min Act: -0.0001

Data Index: 960596 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1100. Min Act: -0.0001

Data Index: 317807 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1347598 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1026. Min Act: -0.0001

Data Index: 809293 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1064. Min Act: -0.0001

Data Index: 168746 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0913. Min Act: -0.0001

Data Index: 267798 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1051. Min Act: -0.0001

Data Index: 738604 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1126. Min Act: -0.0001

Data Index: 527193 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1045. Min Act: -0.0001

Data Index: 498795 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1048. Min Act: -0.0001

Data Index: 978361 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0943. Min Act: -0.0001

Data Index: 16858 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.1048. Min Act: -0.0001

Data Index: 976900 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1073144 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0937. Min Act: -0.0001

Data Index: 812097 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1357072 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.1532. Min Range: -0.1532

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1204299 (C4 (Web Text))

Max Activating Token Index: 489