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

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

Neuron 1165 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: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0002

Data Index: 526891 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1291710 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0744. Min Act: -0.0001

Data Index: 77334 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0753. Min Act: -0.0002

Data Index: 142088 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0729. Min Act: -0.0002

Data Index: 318245 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0690. Min Act: -0.0002

Data Index: 317493 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0715. Min Act: -0.0001

Data Index: 909005 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0717. Min Act: -0.0002

Data Index: 173618 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1134808 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0693. Min Act: -0.0002

Data Index: 653221 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0694. Min Act: -0.0002

Data Index: 268492 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0669. Min Act: -0.0002

Data Index: 113115 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0690. Min Act: -0.0002

Data Index: 48535 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1216319 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0672. Min Act: -0.0002

Data Index: 80283 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0668. Min Act: -0.0001

Data Index: 212196 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1059038 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0659. Min Act: -0.0002

Data Index: 189881 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1107552 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0658. Min Act: -0.0001

Data Index: 239564 (C4 (Web Text))

Max Activating Token Index: 564