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

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

Neuron 458 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: 0.3785. Min Range: -0.3785

Max Act: 0.3785. Min Act: -0.0002

Data Index: 289425 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.3364. Min Act: -0.0002

Data Index: 1321231 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.3487. Min Act: -0.0002

Data Index: 372173 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.3079. Min Act: -0.0002

Data Index: 729624 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.3155. Min Act: -0.0002

Data Index: 537774 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2997. Min Act: -0.0002

Data Index: 840010 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2816. Min Act: -0.0002

Data Index: 760066 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2962. Min Act: -0.0002

Data Index: 1043276 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2925. Min Act: -0.0002

Data Index: 450901 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.3144. Min Act: -0.0002

Data Index: 666736 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2823. Min Act: -0.0002

Data Index: 1340775 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2635. Min Act: -0.0002

Data Index: 71507 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2803. Min Act: -0.0002

Data Index: 1281300 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2774. Min Act: -0.0002

Data Index: 630400 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2855. Min Act: -0.0002

Data Index: 819831 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2776. Min Act: -0.0002

Data Index: 917227 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2646. Min Act: -0.0002

Data Index: 202890 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2736. Min Act: -0.0002

Data Index: 345994 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2706. Min Act: -0.0002

Data Index: 302154 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.3785. Min Range: -0.3785

Max Act: 0.2759. Min Act: -0.0002

Data Index: 174906 (C4 (Web Text))

Max Activating Token Index: 708