Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3275 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6788. Min Act: -0.0001

Data Index: 936963 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1233275 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6487. Min Act: -0.0001

Data Index: 1346291 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6777. Min Act: -0.0001

Data Index: 1156469 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.7272. Min Act: -0.0001

Data Index: 1083897 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6524. Min Act: -0.0001

Data Index: 931847 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6316. Min Act: -0.0001

Data Index: 275585 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6558. Min Act: -0.0001

Data Index: 193566 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6021. Min Act: -0.0001

Data Index: 1082736 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6235. Min Act: -0.0001

Data Index: 785740 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5841. Min Act: -0.0001

Data Index: 139710 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6370. Min Act: -0.0001

Data Index: 175201 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5903. Min Act: -0.0001

Data Index: 1272592 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5876. Min Act: -0.0001

Data Index: 881751 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6251. Min Act: -0.0001

Data Index: 211729 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.6089. Min Act: -0.0001

Data Index: 769006 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5662. Min Act: -0.0001

Data Index: 691218 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5617. Min Act: -0.0001

Data Index: 1204320 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5803. Min Act: -0.0001

Data Index: 271921 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.7272. Min Range: -0.7272

Max Act: 0.5712. Min Act: -0.0001

Data Index: 1003408 (C4 (Web Text))

Max Activating Token Index: 387