Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 499 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0005

Data Index: 336323 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0847. Min Act: -0.0005

Data Index: 116375 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0811. Min Act: -0.0005

Data Index: 1254667 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0756. Min Act: -0.0005

Data Index: 514008 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0794. Min Act: -0.0005

Data Index: 262584 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0792. Min Act: -0.0005

Data Index: 204899 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0767. Min Act: -0.0005

Data Index: 1323098 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0771. Min Act: -0.0005

Data Index: 581895 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0753. Min Act: -0.0005

Data Index: 1245969 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0780. Min Act: -0.0005

Data Index: 183663 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0721. Min Act: -0.0005

Data Index: 701523 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0772. Min Act: -0.0005

Data Index: 1042848 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0741. Min Act: -0.0005

Data Index: 1054312 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0741. Min Act: -0.0005

Data Index: 465728 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0694. Min Act: -0.0005

Data Index: 901143 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0740. Min Act: -0.0005

Data Index: 818961 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0718. Min Act: -0.0005

Data Index: 973792 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0718. Min Act: -0.0005

Data Index: 1112863 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0756. Min Act: -0.0005

Data Index: 861274 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0707. Min Act: -0.0005

Data Index: 390914 (C4 (Web Text))

Max Activating Token Index: 275