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

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

Neuron 3166 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1373. Min Act: -0.0001

Data Index: 542818 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1319. Min Act: -0.0001

Data Index: 180946 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1247. Min Act: -0.0001

Data Index: 1279349 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1217098 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1099. Min Act: -0.0001

Data Index: 691367 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1134. Min Act: -0.0001

Data Index: 838150 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1173. Min Act: -0.0001

Data Index: 459906 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1329312 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1091. Min Act: -0.0001

Data Index: 335716 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1001. Min Act: -0.0001

Data Index: 332344 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1113. Min Act: -0.0001

Data Index: 295440 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1017791 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1101. Min Act: -0.0001

Data Index: 892456 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1061. Min Act: -0.0001

Data Index: 359183 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1130. Min Act: -0.0001

Data Index: 742889 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1093. Min Act: -0.0001

Data Index: 780630 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1015415 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1062. Min Act: -0.0001

Data Index: 866087 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1112. Min Act: -0.0001

Data Index: 793759 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.1373. Min Range: -0.1373

Max Act: 0.1064. Min Act: -0.0001

Data Index: 556340 (C4 (Web Text))

Max Activating Token Index: 10