Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1160092 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1127. Min Act: -0.0001

Data Index: 214825 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1004592 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1188. Min Act: -0.0001

Data Index: 831506 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1186. Min Act: -0.0002

Data Index: 217814 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1334629 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1100. Min Act: -0.0001

Data Index: 55277 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1133. Min Act: -0.0001

Data Index: 440722 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1014. Min Act: -0.0001

Data Index: 544027 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1272317 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1064. Min Act: -0.0001

Data Index: 171572 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1230971 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1193257 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1010. Min Act: -0.0001

Data Index: 496408 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1039. Min Act: -0.0001

Data Index: 146462 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0996. Min Act: -0.0002

Data Index: 188475 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1007. Min Act: -0.0002

Data Index: 891776 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1230085 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1322723 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.1188. Min Range: -0.1188

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1155343 (C4 (Web Text))

Max Activating Token Index: 344