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

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

Neuron 224 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.7467. Min Range: -14.7467

Max Act: 14.7467. Min Act: -0.0000

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 14.7467. Min Range: -14.7467

Max Act: 12.1179. Min Act: 0.0000

Data Index: 1084174 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 14.7467. Min Range: -14.7467

Max Act: 11.3684. Min Act: -0.0000

Data Index: 1315908 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 14.7467. Min Range: -14.7467

Max Act: 8.6033. Min Act: -0.0000

Data Index: 820909 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 14.7467. Min Range: -14.7467

Max Act: 5.8161. Min Act: -0.0000

Data Index: 114437 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 14.7467. Min Range: -14.7467

Max Act: 4.9232. Min Act: -0.0000

Data Index: 1350900 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 14.7467. Min Range: -14.7467

Max Act: 7.0303. Min Act: -0.0000

Data Index: 674202 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 14.7467. Min Range: -14.7467

Max Act: 3.1252. Min Act: 0.0001

Data Index: 18389 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 14.7467. Min Range: -14.7467

Max Act: 3.4679. Min Act: -0.0000

Data Index: 79872 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 14.7467. Min Range: -14.7467

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1217823 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.9721. Min Act: -0.0000

Data Index: 1080092 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1181086 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.5060. Min Act: -0.0000

Data Index: 995042 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.0768. Min Act: -0.0000

Data Index: 326604 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1089403 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.2378. Min Act: -0.0000

Data Index: 738318 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.4391. Min Act: -0.0000

Data Index: 39227 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.1779. Min Act: -0.0000

Data Index: 895422 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 14.7467. Min Range: -14.7467

Max Act: 0.0504. Min Act: -0.0000

Data Index: 272478 (C4 (Web Text))

Max Activating Token Index: 93