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

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

Neuron 1962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1343. Min Act: -0.0001

Data Index: 82879 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1216. Min Act: -0.0001

Data Index: 968164 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1267. Min Act: -0.0002

Data Index: 784344 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1046300 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1171. Min Act: -0.0002

Data Index: 670327 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1117. Min Act: -0.0001

Data Index: 93364 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1126. Min Act: -0.0002

Data Index: 494819 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1143910 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1191. Min Act: -0.0001

Data Index: 269914 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1326260 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1126. Min Act: -0.0002

Data Index: 304486 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1139. Min Act: -0.0001

Data Index: 153943 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1142. Min Act: -0.0002

Data Index: 960634 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1132366 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1054. Min Act: -0.0001

Data Index: 247894 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1059. Min Act: -0.0001

Data Index: 668255 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1089. Min Act: -0.0001

Data Index: 699679 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1083234 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1054. Min Act: -0.0002

Data Index: 514461 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.1343. Min Range: -0.1343

Max Act: 0.1111. Min Act: -0.0001

Data Index: 442808 (C4 (Web Text))

Max Activating Token Index: 955