Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1742 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1254. Min Range: -2.1254

Max Act: 2.1254. Min Act: -0.0000

Data Index: 577802 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.8216. Min Act: -0.0000

Data Index: 1335866 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.6244. Min Act: -0.0000

Data Index: 379853 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.3014. Min Act: -0.0000

Data Index: 1214564 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1251765 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.3512. Min Act: -0.0000

Data Index: 16385 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1326426 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.3408. Min Act: -0.0000

Data Index: 36414 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.3203. Min Act: -0.0000

Data Index: 834871 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1961. Min Act: -0.0000

Data Index: 154918 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1704. Min Act: -0.0000

Data Index: 157629 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1763. Min Act: -0.0000

Data Index: 114786 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1303. Min Act: -0.0000

Data Index: 988746 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1264. Min Act: -0.0000

Data Index: 644066 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1391. Min Act: -0.0000

Data Index: 528855 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1025. Min Act: -0.0000

Data Index: 639439 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.0979. Min Act: -0.0000

Data Index: 513304 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1063852 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1279726 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 2.1254. Min Range: -2.1254

Max Act: 1.1012. Min Act: -0.0000

Data Index: 639522 (C4 (Web Text))

Max Activating Token Index: 819