Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 778 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1251. Min Act: -0.0002

Data Index: 369415 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1225. Min Act: -0.0002

Data Index: 480117 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0002

Data Index: 724953 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1133. Min Act: -0.0002

Data Index: 199278 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1339141 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1042. Min Act: -0.0002

Data Index: 340698 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1079. Min Act: -0.0002

Data Index: 957850 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1119. Min Act: -0.0002

Data Index: 573531 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1046. Min Act: -0.0002

Data Index: 766940 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1096. Min Act: -0.0002

Data Index: 203013 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1129. Min Act: -0.0002

Data Index: 700013 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1087. Min Act: -0.0002

Data Index: 731935 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1070. Min Act: -0.0002

Data Index: 261701 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1038. Min Act: -0.0002

Data Index: 719288 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1024. Min Act: -0.0002

Data Index: 967407 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1312790 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1055189 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1046. Min Act: -0.0002

Data Index: 535911 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1027. Min Act: -0.0002

Data Index: 588951 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1021. Min Act: -0.0002

Data Index: 110037 (C4 (Web Text))

Max Activating Token Index: 23