Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2646 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0002

Data Index: 869846 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1297311 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0861. Min Act: -0.0002

Data Index: 840952 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1067406 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0857. Min Act: -0.0002

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0840. Min Act: -0.0002

Data Index: 491742 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0823. Min Act: -0.0002

Data Index: 521588 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0834. Min Act: -0.0002

Data Index: 456220 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1248766 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0836. Min Act: -0.0002

Data Index: 367806 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0812. Min Act: -0.0002

Data Index: 801545 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0806. Min Act: -0.0002

Data Index: 258442 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0812. Min Act: -0.0002

Data Index: 689872 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0795. Min Act: -0.0002

Data Index: 483380 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0776. Min Act: -0.0002

Data Index: 351983 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0820. Min Act: -0.0002

Data Index: 49538 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0761. Min Act: -0.0002

Data Index: 320113 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0794. Min Act: -0.0002

Data Index: 644783 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0769. Min Act: -0.0002

Data Index: 446203 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0782. Min Act: -0.0002

Data Index: 620877 (C4 (Web Text))

Max Activating Token Index: 934