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

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

Neuron 2212 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: 0.9274. Min Range: -0.9274

Max Act: 0.8841. Min Act: -0.0000

Data Index: 159851 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9274. Min Act: -0.0000

Data Index: 77997 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9058. Min Act: -0.0000

Data Index: 555120 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.9236. Min Act: -0.0000

Data Index: 1038760 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1133337 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7894. Min Act: -0.0000

Data Index: 797431 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8065. Min Act: -0.0000

Data Index: 323702 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8501. Min Act: -0.0000

Data Index: 235266 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7742. Min Act: -0.0000

Data Index: 418607 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7617. Min Act: -0.0000

Data Index: 498172 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8355. Min Act: -0.0000

Data Index: 873490 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1278169 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1003829 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7775. Min Act: -0.0000

Data Index: 291342 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7239. Min Act: -0.0000

Data Index: 144169 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7255. Min Act: -0.0000

Data Index: 131425 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7494. Min Act: -0.0000

Data Index: 333779 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7426. Min Act: -0.0000

Data Index: 582315 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7460. Min Act: -0.0000

Data Index: 825594 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.9274. Min Range: -0.9274

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1251609 (C4 (Web Text))

Max Activating Token Index: 28