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

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

Neuron 3650 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1263. Min Act: -0.0000

Data Index: 286675 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1049839 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1232. Min Act: -0.0000

Data Index: 296566 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1119. Min Act: -0.0001

Data Index: 921470 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1036. Min Act: -0.0000

Data Index: 746523 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1079. Min Act: -0.0000

Data Index: 554742 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1098. Min Act: -0.0000

Data Index: 785922 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1023. Min Act: -0.0001

Data Index: 175845 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1016. Min Act: -0.0001

Data Index: 1278677 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1002. Min Act: -0.0001

Data Index: 928678 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0916. Min Act: -0.0000

Data Index: 136798 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0900. Min Act: -0.0000

Data Index: 114719 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0826. Min Act: -0.0000

Data Index: 940452 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0864. Min Act: -0.0001

Data Index: 508303 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0944. Min Act: -0.0000

Data Index: 700993 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1084788 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0872. Min Act: -0.0000

Data Index: 758800 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1164013 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1312200 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0858. Min Act: -0.0001

Data Index: 312951 (C4 (Web Text))

Max Activating Token Index: 656