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

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

Neuron 1763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: -0.0005

Data Index: 728068 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0995. Min Act: -0.0005

Data Index: 201327 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0888. Min Act: -0.0005

Data Index: 578241 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0911. Min Act: -0.0005

Data Index: 934618 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0910. Min Act: -0.0005

Data Index: 1313869 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0836. Min Act: -0.0005

Data Index: 659052 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0823. Min Act: -0.0005

Data Index: 502763 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0860. Min Act: -0.0005

Data Index: 1185113 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0780. Min Act: -0.0005

Data Index: 233526 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0812. Min Act: -0.0005

Data Index: 1034021 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0772. Min Act: -0.0005

Data Index: 1201797 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0752. Min Act: -0.0005

Data Index: 1119720 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0795. Min Act: -0.0005

Data Index: 922098 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0765. Min Act: -0.0005

Data Index: 203285 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0746. Min Act: -0.0005

Data Index: 817273 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0716. Min Act: -0.0005

Data Index: 906940 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0711. Min Act: -0.0005

Data Index: 520349 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0753. Min Act: -0.0005

Data Index: 233747 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0671. Min Act: -0.0005

Data Index: 315083 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0693. Min Act: -0.0005

Data Index: 163105 (C4 (Web Text))

Max Activating Token Index: 145