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

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

Neuron 1664 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: 0.9045. Min Range: -0.9045

Max Act: 0.9045. Min Act: -0.0001

Data Index: 127401 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.8144. Min Act: -0.0001

Data Index: 635092 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1003387 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7571. Min Act: -0.0001

Data Index: 966000 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7429. Min Act: -0.0001

Data Index: 846743 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.8111. Min Act: -0.0001

Data Index: 1000737 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7647. Min Act: -0.0001

Data Index: 904382 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7486. Min Act: -0.0001

Data Index: 932829 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7279. Min Act: -0.0001

Data Index: 233699 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7768. Min Act: -0.0001

Data Index: 896613 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1054635 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7928. Min Act: -0.0001

Data Index: 989559 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.8150. Min Act: -0.0001

Data Index: 1026737 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.8128. Min Act: -0.0001

Data Index: 917244 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7705. Min Act: -0.0001

Data Index: 524688 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7759. Min Act: -0.0001

Data Index: 62173 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7562. Min Act: -0.0001

Data Index: 217461 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7465. Min Act: -0.0001

Data Index: 596889 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7451. Min Act: -0.0001

Data Index: 529243 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7557. Min Act: -0.0001

Data Index: 535077 (C4 (Web Text))

Max Activating Token Index: 369