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

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

Neuron 2009 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.5343. Min Act: -0.0001

Data Index: 339269 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.5121. Min Act: -0.0001

Data Index: 654212 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4847. Min Act: -0.0002

Data Index: 35191 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4807. Min Act: -0.0002

Data Index: 296591 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4751. Min Act: -0.0001

Data Index: 855390 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4651. Min Act: -0.0001

Data Index: 555734 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4567. Min Act: -0.0002

Data Index: 708593 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4416. Min Act: -0.0002

Data Index: 146096 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4725. Min Act: -0.0002

Data Index: 299672 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4828. Min Act: -0.0001

Data Index: 1335606 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4333. Min Act: -0.0001

Data Index: 735952 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4563. Min Act: -0.0001

Data Index: 819381 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4636. Min Act: -0.0002

Data Index: 307529 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4622. Min Act: -0.0002

Data Index: 530104 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4485. Min Act: -0.0001

Data Index: 918611 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4437. Min Act: -0.0002

Data Index: 946886 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4580. Min Act: -0.0002

Data Index: 1278972 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4686. Min Act: -0.0001

Data Index: 1071226 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4376. Min Act: -0.0001

Data Index: 11378 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.5343. Min Range: -0.5343

Max Act: 0.4494. Min Act: -0.0002

Data Index: 638307 (C4 (Web Text))

Max Activating Token Index: 213