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

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

Neuron 3526 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: 1.4781. Min Range: -1.4781

Max Act: 1.4781. Min Act: -0.0001

Data Index: 446361 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2505. Min Act: -0.0001

Data Index: 1144177 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.3225. Min Act: -0.0001

Data Index: 948316 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1632. Min Act: -0.0001

Data Index: 311657 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0100. Min Act: -0.0001

Data Index: 767959 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0860. Min Act: -0.0001

Data Index: 1343342 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0203. Min Act: -0.0001

Data Index: 1358991 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2629. Min Act: -0.0001

Data Index: 1000697 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.1137. Min Act: -0.0001

Data Index: 331839 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.2021. Min Act: -0.0001

Data Index: 739456 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0326. Min Act: -0.0001

Data Index: 378695 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0188. Min Act: -0.0001

Data Index: 138788 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0969. Min Act: -0.0001

Data Index: 1099668 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0292. Min Act: -0.0001

Data Index: 910116 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0425. Min Act: -0.0001

Data Index: 404508 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.4781. Min Range: -1.4781

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1276441 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1181624 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.4781. Min Range: -1.4781

Max Act: 0.9917. Min Act: -0.0001

Data Index: 527073 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 1.4781. Min Range: -1.4781

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1102126 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 1.4781. Min Range: -1.4781

Max Act: 1.0536. Min Act: -0.0001

Data Index: 494455 (C4 (Web Text))

Max Activating Token Index: 76