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

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

Neuron 1996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1516. Min Act: -0.0001

Data Index: 270440 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1423. Min Act: 0.0001

Data Index: 490682 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1316. Min Act: 0.0002

Data Index: 804905 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1260. Min Act: 0.0001

Data Index: 109856 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1207. Min Act: -0.0001

Data Index: 1027902 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1461313 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1245. Min Act: -0.0000

Data Index: 911100 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1209. Min Act: 0.0000

Data Index: 1442278 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1237. Min Act: 0.0000

Data Index: 1525429 (Python Code)

Max Activating Token Index: 726

Text #9

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1150. Min Act: -0.0001

Data Index: 49152 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1190. Min Act: -0.0001

Data Index: 370853 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1614491 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1184. Min Act: -0.0001

Data Index: 989432 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1178. Min Act: -0.0001

Data Index: 880523 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1097713 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1404615 (Python Code)

Max Activating Token Index: 855

Text #16

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1608743 (Python Code)

Max Activating Token Index: 659

Text #18

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1537516 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1032731 (C4 (Web Text))

Max Activating Token Index: 752