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

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

Neuron 221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0002

Data Index: 616845 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0773. Min Act: -0.0002

Data Index: 950193 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1001202 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0714. Min Act: -0.0002

Data Index: 189275 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0734. Min Act: -0.0002

Data Index: 707960 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0719. Min Act: -0.0002

Data Index: 769964 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0696. Min Act: -0.0002

Data Index: 662568 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0674. Min Act: -0.0002

Data Index: 509754 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0658. Min Act: -0.0002

Data Index: 539910 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1114995 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0660. Min Act: -0.0002

Data Index: 774857 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0648. Min Act: -0.0001

Data Index: 389442 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1288418 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0654. Min Act: -0.0002

Data Index: 505095 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0649. Min Act: -0.0002

Data Index: 246415 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0663. Min Act: -0.0001

Data Index: 826093 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0659. Min Act: -0.0002

Data Index: 780363 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0663. Min Act: -0.0002

Data Index: 257707 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0642. Min Act: -0.0002

Data Index: 519149 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0625. Min Act: -0.0002

Data Index: 664242 (C4 (Web Text))

Max Activating Token Index: 93