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

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

Neuron 4043 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1039026 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1670. Min Act: -0.0001

Data Index: 897062 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1352. Min Act: -0.0001

Data Index: 716839 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1317. Min Act: -0.0001

Data Index: 1159515 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1282. Min Act: -0.0001

Data Index: 642262 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1279. Min Act: -0.0000

Data Index: 865218 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1284. Min Act: -0.0000

Data Index: 611084 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1256. Min Act: -0.0001

Data Index: 425986 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1118544 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1486819 (Python Code)

Max Activating Token Index: 629

Text #10

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1149276 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1083. Min Act: -0.0001

Data Index: 80870 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1088. Min Act: -0.0001

Data Index: 13756 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1186547 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1119. Min Act: -0.0001

Data Index: 944659 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1083. Min Act: -0.0001

Data Index: 759419 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1038. Min Act: -0.0001

Data Index: 201302 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1112. Min Act: -0.0001

Data Index: 859084 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1316870 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.2196. Min Range: -0.2196

Max Act: 0.1032. Min Act: -0.0000

Data Index: 958253 (C4 (Web Text))

Max Activating Token Index: 111