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

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

Neuron 4656 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: 0.0832. Min Range: -0.0832

Max Act: 0.0832. Min Act: -0.0003

Data Index: 250467 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0787. Min Act: -0.0002

Data Index: 929179 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0795. Min Act: -0.0003

Data Index: 38496 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0736. Min Act: -0.0003

Data Index: 697648 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0721. Min Act: -0.0003

Data Index: 379490 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0768. Min Act: -0.0003

Data Index: 542947 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0688. Min Act: -0.0002

Data Index: 902764 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0714. Min Act: -0.0003

Data Index: 950431 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0699. Min Act: -0.0003

Data Index: 884789 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0695. Min Act: -0.0003

Data Index: 913197 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0672. Min Act: -0.0003

Data Index: 980337 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0698. Min Act: -0.0002

Data Index: 909042 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0689. Min Act: -0.0002

Data Index: 604034 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0686. Min Act: -0.0003

Data Index: 359090 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1228044 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1001381 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0658. Min Act: -0.0003

Data Index: 924046 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0705. Min Act: -0.0003

Data Index: 286463 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0667. Min Act: -0.0003

Data Index: 484408 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.0832. Min Range: -0.0832

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1145947 (C4 (Web Text))

Max Activating Token Index: 207