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

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

Neuron 486 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1284. Min Act: -0.0001

Data Index: 517698 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1287. Min Act: -0.0001

Data Index: 411246 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1217784 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1155. Min Act: -0.0001

Data Index: 708243 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1148. Min Act: -0.0001

Data Index: 461955 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1230. Min Act: -0.0001

Data Index: 515278 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1159. Min Act: -0.0001

Data Index: 604520 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1199. Min Act: -0.0001

Data Index: 537663 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1147. Min Act: -0.0001

Data Index: 682780 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1152. Min Act: -0.0001

Data Index: 395760 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1152. Min Act: -0.0001

Data Index: 728247 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0995. Min Act: -0.0001

Data Index: 823395 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1029. Min Act: -0.0001

Data Index: 888990 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1058. Min Act: -0.0001

Data Index: 993656 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1096. Min Act: -0.0001

Data Index: 246647 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1179001 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1045. Min Act: -0.0001

Data Index: 510490 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1172621 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1109. Min Act: -0.0001

Data Index: 670874 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1049. Min Act: -0.0001

Data Index: 407423 (C4 (Web Text))

Max Activating Token Index: 302