Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1448 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0862. Min Act: -0.0003

Data Index: 608453 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0842. Min Act: -0.0003

Data Index: 775133 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0788. Min Act: -0.0003

Data Index: 1324160 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0809. Min Act: -0.0003

Data Index: 329480 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0805. Min Act: -0.0003

Data Index: 994020 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0769. Min Act: -0.0003

Data Index: 518246 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0756. Min Act: -0.0003

Data Index: 162856 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0807. Min Act: -0.0004

Data Index: 400121 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0805. Min Act: -0.0004

Data Index: 568143 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0799. Min Act: -0.0003

Data Index: 1146496 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0772. Min Act: -0.0003

Data Index: 612855 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0808. Min Act: -0.0003

Data Index: 713563 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0780. Min Act: -0.0003

Data Index: 668902 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0743. Min Act: -0.0003

Data Index: 960682 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0794. Min Act: -0.0003

Data Index: 242592 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0757. Min Act: -0.0003

Data Index: 936985 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0783. Min Act: -0.0003

Data Index: 306351 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0795. Min Act: -0.0003

Data Index: 1130464 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0782. Min Act: -0.0003

Data Index: 704510 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0862. Min Range: -0.0862

Max Act: 0.0715. Min Act: -0.0004

Data Index: 819196 (C4 (Web Text))

Max Activating Token Index: 337