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

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

Neuron 1362 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1386. Min Act: -0.0003

Data Index: 1007753 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1256. Min Act: -0.0003

Data Index: 1102245 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1358. Min Act: -0.0003

Data Index: 1239434 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1178. Min Act: -0.0003

Data Index: 920623 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1214. Min Act: -0.0003

Data Index: 1112509 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1287. Min Act: -0.0003

Data Index: 265531 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1063. Min Act: -0.0003

Data Index: 459502 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1127. Min Act: -0.0003

Data Index: 373006 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1106. Min Act: -0.0003

Data Index: 323394 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1153. Min Act: -0.0003

Data Index: 206099 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1161. Min Act: -0.0003

Data Index: 798343 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1021. Min Act: -0.0003

Data Index: 474310 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1051. Min Act: -0.0003

Data Index: 253445 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1058. Min Act: -0.0003

Data Index: 1117226 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1019. Min Act: -0.0003

Data Index: 284206 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1061. Min Act: -0.0003

Data Index: 1353042 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.0988. Min Act: -0.0003

Data Index: 1342553 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1114. Min Act: -0.0003

Data Index: 410202 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1030. Min Act: -0.0003

Data Index: 578659 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.1386. Min Range: -0.1386

Max Act: 0.1107. Min Act: -0.0003

Data Index: 412477 (C4 (Web Text))

Max Activating Token Index: 268