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

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

Neuron 1560 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: 1.9620. Min Range: -1.9620

Max Act: 1.7926. Min Act: -0.0001

Data Index: 133508 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9620. Min Act: -0.0001

Data Index: 1086725 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.8553. Min Act: -0.0001

Data Index: 1327926 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7053. Min Act: -0.0001

Data Index: 490425 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.9040. Min Act: -0.0001

Data Index: 753150 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7068. Min Act: -0.0001

Data Index: 410535 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7368. Min Act: -0.0001

Data Index: 594439 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.6116. Min Act: -0.0001

Data Index: 604357 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7408. Min Act: -0.0001

Data Index: 391030 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5835. Min Act: -0.0001

Data Index: 1188971 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7749. Min Act: -0.0001

Data Index: 125036 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7290. Min Act: -0.0001

Data Index: 388893 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7212. Min Act: -0.0001

Data Index: 880032 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5414. Min Act: -0.0001

Data Index: 790635 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.6175. Min Act: -0.0001

Data Index: 276777 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7463. Min Act: -0.0001

Data Index: 54126 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.7979. Min Act: -0.0001

Data Index: 666117 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.5610. Min Act: -0.0001

Data Index: 1341379 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.6999. Min Act: -0.0001

Data Index: 1340932 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.9620. Min Range: -1.9620

Max Act: 1.6969. Min Act: -0.0001

Data Index: 156805 (C4 (Web Text))

Max Activating Token Index: 758