Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1310 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1144. Min Act: -0.0001

Data Index: 434055 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1214. Min Act: -0.0001

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1135. Min Act: -0.0001

Data Index: 64499 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1100. Min Act: -0.0001

Data Index: 319758 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1090788 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1090. Min Act: -0.0001

Data Index: 554961 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1133. Min Act: -0.0001

Data Index: 65514 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1100. Min Act: -0.0001

Data Index: 593192 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1095. Min Act: -0.0001

Data Index: 667229 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1096. Min Act: -0.0001

Data Index: 396252 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1002. Min Act: -0.0001

Data Index: 1329851 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1268798 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1047. Min Act: -0.0001

Data Index: 655818 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1094. Min Act: -0.0001

Data Index: 630269 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1040. Min Act: -0.0001

Data Index: 689787 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1078. Min Act: -0.0001

Data Index: 73041 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1065. Min Act: -0.0001

Data Index: 197746 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1027. Min Act: -0.0001

Data Index: 852511 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1055. Min Act: -0.0001

Data Index: 430525 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1018. Min Act: -0.0001

Data Index: 679517 (C4 (Web Text))

Max Activating Token Index: 166