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

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

Neuron 2695 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1112. Min Act: -0.0001

Data Index: 954362 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1146. Min Act: -0.0001

Data Index: 1348677 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1310. Min Act: -0.0001

Data Index: 557344 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1246. Min Act: -0.0001

Data Index: 174250 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1228. Min Act: -0.0001

Data Index: 552954 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1298. Min Act: -0.0001

Data Index: 22530 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0912. Min Act: -0.0001

Data Index: 107868 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1239513 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1136. Min Act: -0.0001

Data Index: 285867 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1195784 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1073. Min Act: -0.0001

Data Index: 155024 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1091942 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1053. Min Act: -0.0001

Data Index: 843574 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0983. Min Act: -0.0001

Data Index: 884652 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1006. Min Act: -0.0001

Data Index: 274515 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1101027 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1277641 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0910. Min Act: -0.0001

Data Index: 984566 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0918. Min Act: -0.0001

Data Index: 409145 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 0.1310. Min Range: -0.1310

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1219338 (C4 (Web Text))

Max Activating Token Index: 337