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

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

Neuron 4238 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0002

Data Index: 6347 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1177825 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1351502 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0756. Min Act: -0.0002

Data Index: 355951 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0740. Min Act: -0.0002

Data Index: 930488 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1333585 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1256834 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1249548 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1098120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0664. Min Act: -0.0002

Data Index: 126979 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1219831 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0652. Min Act: -0.0001

Data Index: 673584 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0651. Min Act: -0.0002

Data Index: 298745 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0676. Min Act: -0.0002

Data Index: 521108 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0671. Min Act: -0.0002

Data Index: 695453 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0637. Min Act: -0.0002

Data Index: 306015 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0631. Min Act: -0.0002

Data Index: 954297 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0629. Min Act: -0.0002

Data Index: 860388 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0626. Min Act: -0.0002

Data Index: 177120 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1071618 (C4 (Web Text))

Max Activating Token Index: 224