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

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

Neuron 2559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1072652 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1240. Min Act: -0.0002

Data Index: 228721 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1200170 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1209. Min Act: -0.0002

Data Index: 671909 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1156. Min Act: -0.0002

Data Index: 935778 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1103190 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1176. Min Act: -0.0002

Data Index: 473768 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1194. Min Act: -0.0002

Data Index: 929824 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1144. Min Act: -0.0002

Data Index: 673877 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1149. Min Act: -0.0002

Data Index: 514105 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1101. Min Act: -0.0002

Data Index: 426550 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1134. Min Act: -0.0002

Data Index: 613243 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1085243 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1127. Min Act: -0.0002

Data Index: 94385 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1112. Min Act: -0.0002

Data Index: 849904 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1205785 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1072. Min Act: -0.0002

Data Index: 368685 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1110. Min Act: -0.0002

Data Index: 975350 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1102. Min Act: -0.0002

Data Index: 555964 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1067781 (C4 (Web Text))

Max Activating Token Index: 163