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

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

Neuron 5049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1168. Min Act: -0.0000

Data Index: 479880 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1163. Min Act: -0.0000

Data Index: 262574 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1063. Min Act: -0.0000

Data Index: 268745 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1252299 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1070. Min Act: -0.0000

Data Index: 1257925 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1097. Min Act: -0.0000

Data Index: 915608 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1059. Min Act: -0.0000

Data Index: 82175 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1452 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1095. Min Act: -0.0000

Data Index: 813383 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1093467 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1232272 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1064. Min Act: -0.0000

Data Index: 918094 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1061. Min Act: -0.0000

Data Index: 500759 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1039. Min Act: -0.0000

Data Index: 371079 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1014. Min Act: -0.0000

Data Index: 800725 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.1036. Min Act: -0.0000

Data Index: 612011 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1159739 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0982. Min Act: -0.0000

Data Index: 698775 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1121881 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 0.1168. Min Range: -0.1168

Max Act: 0.0979. Min Act: -0.0000

Data Index: 697376 (C4 (Web Text))

Max Activating Token Index: 526