Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2527 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.2243. Min Act: -0.0000

Data Index: 745624 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1135843 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.1465. Min Act: -0.0000

Data Index: 755959 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.0541. Min Act: -0.0000

Data Index: 1323505 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9572. Min Act: -0.0000

Data Index: 86231 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.2243. Min Range: -1.2243

Max Act: 1.0254. Min Act: -0.0000

Data Index: 645298 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8963. Min Act: -0.0000

Data Index: 658639 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9411. Min Act: -0.0000

Data Index: 385964 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1291611 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8902. Min Act: -0.0001

Data Index: 983226 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1199205 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8582. Min Act: -0.0000

Data Index: 126397 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8257. Min Act: -0.0000

Data Index: 977151 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.9034. Min Act: -0.0000

Data Index: 755883 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1268462 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8431. Min Act: -0.0000

Data Index: 123566 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1179050 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8443. Min Act: -0.0000

Data Index: 840362 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1075872 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 1.2243. Min Range: -1.2243

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1123808 (C4 (Web Text))

Max Activating Token Index: 482