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

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

Neuron 2470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1560. Min Act: -0.0000

Data Index: 97890 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1295488 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1587. Min Act: -0.0000

Data Index: 883378 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1306. Min Act: -0.0000

Data Index: 761275 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1258. Min Act: -0.0000

Data Index: 165356 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1076. Min Act: -0.0000

Data Index: 471853 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1112. Min Act: -0.0000

Data Index: 521699 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1091. Min Act: -0.0000

Data Index: 864182 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1126. Min Act: -0.0000

Data Index: 586842 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1038. Min Act: -0.0000

Data Index: 440736 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1057. Min Act: -0.0000

Data Index: 372203 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1083. Min Act: -0.0000

Data Index: 557696 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1138351 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1136558 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0965. Min Act: -0.0000

Data Index: 777029 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1309128 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1043. Min Act: -0.0000

Data Index: 480319 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1009. Min Act: -0.0000

Data Index: 438249 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1341258 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0977. Min Act: -0.0000

Data Index: 356312 (C4 (Web Text))

Max Activating Token Index: 521