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

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

Neuron 721 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: 0.1491. Min Range: -0.1491

Max Act: 0.1491. Min Act: -0.0003

Data Index: 549464 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1313. Min Act: -0.0003

Data Index: 158356 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1243. Min Act: -0.0003

Data Index: 639779 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1199. Min Act: -0.0003

Data Index: 1228018 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1203. Min Act: -0.0003

Data Index: 1305146 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1123. Min Act: -0.0003

Data Index: 886410 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1131. Min Act: -0.0003

Data Index: 1134269 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1135. Min Act: -0.0003

Data Index: 264797 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1155. Min Act: -0.0003

Data Index: 57543 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1126. Min Act: -0.0003

Data Index: 142717 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1116. Min Act: -0.0003

Data Index: 37120 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1065. Min Act: -0.0003

Data Index: 212600 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1103. Min Act: -0.0003

Data Index: 1164764 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1238421 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1013. Min Act: -0.0003

Data Index: 1278093 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1086. Min Act: -0.0003

Data Index: 328612 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1047. Min Act: -0.0003

Data Index: 1314105 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1031. Min Act: -0.0003

Data Index: 99314 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1025. Min Act: -0.0003

Data Index: 477853 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.1491. Min Range: -0.1491

Max Act: 0.1054. Min Act: -0.0003

Data Index: 940680 (C4 (Web Text))

Max Activating Token Index: 247