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

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

Neuron 3982 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0003

Data Index: 83637 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1153863 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0319. Min Act: -0.0003

Data Index: 768220 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0323. Min Act: -0.0003

Data Index: 955137 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0317. Min Act: -0.0003

Data Index: 760495 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1166738 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0300. Min Act: -0.0003

Data Index: 856274 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0304. Min Act: -0.0003

Data Index: 643754 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1302768 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0281. Min Act: -0.0003

Data Index: 628212 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0285. Min Act: -0.0003

Data Index: 481121 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1008993 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0281. Min Act: -0.0004

Data Index: 840964 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0272. Min Act: -0.0003

Data Index: 699610 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0279. Min Act: -0.0003

Data Index: 137783 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0260. Min Act: -0.0003

Data Index: 813816 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1204234 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0279. Min Act: -0.0003

Data Index: 547017 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1130766 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0273. Min Act: -0.0004

Data Index: 377459 (C4 (Web Text))

Max Activating Token Index: 855