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

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

Neuron 2464 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1564. Min Act: -0.0001

Data Index: 285945 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1114431 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1075549 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1272. Min Act: -0.0001

Data Index: 26619 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1237. Min Act: -0.0001

Data Index: 876457 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1229. Min Act: -0.0001

Data Index: 534536 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1060770 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1185597 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1139. Min Act: -0.0001

Data Index: 213764 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1149. Min Act: -0.0001

Data Index: 929306 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1114. Min Act: -0.0001

Data Index: 862798 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1044. Min Act: -0.0001

Data Index: 626247 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1093809 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1068. Min Act: -0.0001

Data Index: 281286 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1065. Min Act: -0.0001

Data Index: 689238 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1067144 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1025. Min Act: -0.0001

Data Index: 294325 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1009. Min Act: -0.0001

Data Index: 141141 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1124. Min Act: -0.0001

Data Index: 616 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1029. Min Act: -0.0001

Data Index: 20581 (C4 (Web Text))

Max Activating Token Index: 216