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

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

Neuron 647 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: 0.1272. Min Range: -0.1272

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1385485 (Python Code)

Max Activating Token Index: 637

Text #1

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1388333 (Python Code)

Max Activating Token Index: 694

Text #2

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1383639 (Python Code)

Max Activating Token Index: 107

Text #3

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1531122 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1424443 (Python Code)

Max Activating Token Index: 838

Text #5

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1098. Min Act: -0.0002

Data Index: 1533704 (Python Code)

Max Activating Token Index: 291

Text #6

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1380276 (Python Code)

Max Activating Token Index: 939

Text #7

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1591091 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1383896 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1091. Min Act: -0.0002

Data Index: 1413222 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1107. Min Act: -0.0002

Data Index: 1454737 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1626191 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1374114 (Python Code)

Max Activating Token Index: 1015

Text #13

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1564353 (Python Code)

Max Activating Token Index: 346

Text #14

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1646918 (Python Code)

Max Activating Token Index: 880

Text #15

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1656608 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1431525 (Python Code)

Max Activating Token Index: 873

Text #17

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1488890 (Python Code)

Max Activating Token Index: 431

Text #18

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1549221 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1567229 (Python Code)

Max Activating Token Index: 617