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

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

Neuron 313 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: 0.1221. Min Range: -0.1221

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1016278 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0001

Data Index: 176208 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1169857 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1142. Min Act: -0.0001

Data Index: 460456 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1141. Min Act: -0.0001

Data Index: 598893 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1060843 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1315969 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1136. Min Act: -0.0001

Data Index: 797523 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1129. Min Act: -0.0001

Data Index: 669420 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1069. Min Act: -0.0001

Data Index: 717923 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1029. Min Act: -0.0001

Data Index: 957451 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1060. Min Act: -0.0001

Data Index: 696169 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1095. Min Act: -0.0001

Data Index: 987370 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1087. Min Act: -0.0001

Data Index: 453467 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1131. Min Act: -0.0001

Data Index: 994647 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1080. Min Act: -0.0001

Data Index: 63277 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1077. Min Act: -0.0001

Data Index: 211945 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0924. Min Act: -0.0001

Data Index: 859022 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0985. Min Act: -0.0001

Data Index: 1114110 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1021. Min Act: -0.0001

Data Index: 812187 (C4 (Web Text))

Max Activating Token Index: 89