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

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

Neuron 1093 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: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0002

Data Index: 688492 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1290076 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0700. Min Act: -0.0002

Data Index: 133861 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0793. Min Act: -0.0002

Data Index: 14739 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0826. Min Act: -0.0002

Data Index: 595943 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0762. Min Act: -0.0002

Data Index: 853439 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0751. Min Act: -0.0002

Data Index: 971682 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1033996 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1103557 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0713. Min Act: -0.0002

Data Index: 43026 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0735. Min Act: -0.0002

Data Index: 891234 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1146474 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0741. Min Act: -0.0002

Data Index: 337292 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0756. Min Act: -0.0002

Data Index: 29960 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0744. Min Act: -0.0002

Data Index: 972009 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0736. Min Act: -0.0002

Data Index: 379189 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0713. Min Act: -0.0002

Data Index: 862156 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0682. Min Act: -0.0002

Data Index: 227336 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0757. Min Act: -0.0002

Data Index: 5972 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1084959 (C4 (Web Text))

Max Activating Token Index: 160