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

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

Neuron 353 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: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0002

Data Index: 866676 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0769. Min Act: -0.0003

Data Index: 383782 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0773. Min Act: -0.0004

Data Index: 1031887 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0755. Min Act: -0.0002

Data Index: 678549 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0759. Min Act: -0.0002

Data Index: 763359 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0755. Min Act: -0.0003

Data Index: 173017 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0718. Min Act: -0.0002

Data Index: 763448 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0704. Min Act: -0.0003

Data Index: 415858 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0727. Min Act: -0.0003

Data Index: 39337 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1098763 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1036374 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0705. Min Act: -0.0003

Data Index: 558421 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0708. Min Act: -0.0003

Data Index: 345348 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0709. Min Act: -0.0003

Data Index: 690136 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1162948 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0706. Min Act: -0.0002

Data Index: 917471 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0703. Min Act: -0.0002

Data Index: 71801 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0707. Min Act: -0.0003

Data Index: 29493 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0700. Min Act: -0.0003

Data Index: 385443 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0703. Min Act: -0.0003

Data Index: 819925 (C4 (Web Text))

Max Activating Token Index: 439