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

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

Neuron 4919 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: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1246213 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1342. Min Act: -0.0000

Data Index: 240432 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1258. Min Act: -0.0000

Data Index: 812855 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1208. Min Act: -0.0000

Data Index: 214805 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1257. Min Act: -0.0000

Data Index: 958786 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1064. Min Act: -0.0000

Data Index: 821797 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1022. Min Act: -0.0000

Data Index: 520083 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1077. Min Act: -0.0000

Data Index: 362780 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0985. Min Act: -0.0000

Data Index: 935503 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1122502 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0873. Min Act: -0.0000

Data Index: 107717 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0996. Min Act: -0.0000

Data Index: 932585 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0940. Min Act: -0.0000

Data Index: 764309 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0911. Min Act: -0.0000

Data Index: 289891 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1353262 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0893. Min Act: -0.0000

Data Index: 685763 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0865. Min Act: -0.0000

Data Index: 164416 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0920. Min Act: -0.0000

Data Index: 480990 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1080630 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0879. Min Act: -0.0000

Data Index: 310227 (C4 (Web Text))

Max Activating Token Index: 40