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

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

Neuron 2396 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: 0.1143. Min Range: -0.1143

Max Act: 0.1028. Min Act: -0.0002

Data Index: 933530 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1106. Min Act: -0.0002

Data Index: 251298 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0002

Data Index: 872690 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1029084 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1054846 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0970. Min Act: -0.0002

Data Index: 984272 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0952. Min Act: -0.0002

Data Index: 59241 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0900. Min Act: -0.0002

Data Index: 877994 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0912. Min Act: -0.0002

Data Index: 520617 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1018. Min Act: -0.0002

Data Index: 281543 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0989. Min Act: -0.0002

Data Index: 664917 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1325607 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0914. Min Act: -0.0002

Data Index: 252858 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1079852 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0941. Min Act: -0.0002

Data Index: 840539 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1324719 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0975. Min Act: -0.0002

Data Index: 171039 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0788. Min Act: -0.0002

Data Index: 695712 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0869. Min Act: -0.0002

Data Index: 128588 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1288373 (C4 (Web Text))

Max Activating Token Index: 792