Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1746. Min Act: -0.0000

Data Index: 337616 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1476. Min Act: -0.0000

Data Index: 794165 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1525. Min Act: -0.0000

Data Index: 732373 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1343. Min Act: -0.0000

Data Index: 72966 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1263. Min Act: -0.0000

Data Index: 889261 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1220. Min Act: -0.0000

Data Index: 224971 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1068. Min Act: -0.0000

Data Index: 10095 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1130. Min Act: -0.0000

Data Index: 729339 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1200151 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1488210 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1227. Min Act: -0.0000

Data Index: 992663 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1185. Min Act: -0.0000

Data Index: 436056 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1496428 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1057. Min Act: -0.0000

Data Index: 875071 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1015. Min Act: -0.0000

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1012. Min Act: -0.0001

Data Index: 651093 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1045. Min Act: -0.0000

Data Index: 278153 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1025594 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.1009. Min Act: -0.0000

Data Index: 391410 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.1746. Min Range: -0.1746

Max Act: 0.0881. Min Act: -0.0001

Data Index: 684348 (C4 (Web Text))

Max Activating Token Index: 734