Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2619 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0001

Data Index: 729191 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1452. Min Act: -0.0001

Data Index: 278727 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1436. Min Act: -0.0000

Data Index: 7633 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1268526 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1040984 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1350. Min Act: -0.0000

Data Index: 616440 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1317. Min Act: -0.0001

Data Index: 872194 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1310. Min Act: -0.0001

Data Index: 569779 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1313. Min Act: -0.0001

Data Index: 448566 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1235. Min Act: -0.0001

Data Index: 93108 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1013124 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1264. Min Act: -0.0001

Data Index: 322220 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1217. Min Act: -0.0001

Data Index: 502075 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1246. Min Act: -0.0001

Data Index: 635060 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1251. Min Act: -0.0001

Data Index: 188603 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1246. Min Act: -0.0001

Data Index: 816591 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1193. Min Act: -0.0001

Data Index: 954328 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1180974 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1200608 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1231. Min Act: -0.0001

Data Index: 892167 (C4 (Web Text))

Max Activating Token Index: 805