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

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

Neuron 4205 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0844. Min Range: -1.0844

Max Act: 1.0580. Min Act: -0.0000

Data Index: 28629 (C4 (Web Text))

Max Activating Token Index: 963

Text #1

Max Range: 1.0844. Min Range: -1.0844

Max Act: 1.0844. Min Act: -0.0000

Data Index: 964941 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.9164. Min Act: 0.0000

Data Index: 80809 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1205882 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7917. Min Act: -0.0000

Data Index: 170502 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7676. Min Act: -0.0000

Data Index: 444671 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7159. Min Act: -0.0000

Data Index: 737445 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7292. Min Act: -0.0000

Data Index: 118696 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7244. Min Act: -0.0000

Data Index: 420860 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7194. Min Act: -0.0000

Data Index: 1304230 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7125. Min Act: -0.0000

Data Index: 485747 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7177. Min Act: -0.0000

Data Index: 639577 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7343. Min Act: -0.0000

Data Index: 175751 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1141300 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7276. Min Act: -0.0000

Data Index: 964532 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.6945. Min Act: -0.0000

Data Index: 725998 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7132. Min Act: -0.0000

Data Index: 258623 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.6909. Min Act: -0.0000

Data Index: 622492 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.6938. Min Act: -0.0000

Data Index: 364232 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.0844. Min Range: -1.0844

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1359135 (C4 (Web Text))

Max Activating Token Index: 820