Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 179 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1305739 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1102. Min Act: -0.0001

Data Index: 655188 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1152. Min Act: -0.0001

Data Index: 139152 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1023. Min Act: -0.0001

Data Index: 684202 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1092. Min Act: -0.0001

Data Index: 291607 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1395 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0901. Min Act: -0.0001

Data Index: 422240 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0865. Min Act: -0.0001

Data Index: 628102 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0799. Min Act: -0.0001

Data Index: 937140 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1017629 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0815. Min Act: -0.0001

Data Index: 948010 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0728. Min Act: -0.0001

Data Index: 20464 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1315891 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0820. Min Act: -0.0001

Data Index: 985464 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0766. Min Act: -0.0001

Data Index: 74711 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0756. Min Act: -0.0001

Data Index: 884764 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0745. Min Act: -0.0001

Data Index: 503912 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0729. Min Act: -0.0001

Data Index: 196854 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0708. Min Act: -0.0001

Data Index: 813866 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0786. Min Act: -0.0001

Data Index: 459026 (C4 (Web Text))

Max Activating Token Index: 177