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

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

Neuron 684 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: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0005

Data Index: 491826 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0813. Min Act: -0.0005

Data Index: 1098911 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0769. Min Act: -0.0005

Data Index: 216064 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0732. Min Act: -0.0005

Data Index: 299090 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0780. Min Act: -0.0005

Data Index: 268186 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0783. Min Act: -0.0005

Data Index: 109313 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0771. Min Act: -0.0005

Data Index: 633538 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0738. Min Act: -0.0005

Data Index: 479334 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0724. Min Act: -0.0005

Data Index: 345497 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0736. Min Act: -0.0005

Data Index: 330299 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0732. Min Act: -0.0005

Data Index: 1059990 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0720. Min Act: -0.0005

Data Index: 732115 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0729. Min Act: -0.0005

Data Index: 1315605 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0691. Min Act: -0.0005

Data Index: 581090 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0737. Min Act: -0.0005

Data Index: 853100 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0704. Min Act: -0.0005

Data Index: 999148 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0700. Min Act: -0.0005

Data Index: 599566 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0692. Min Act: -0.0005

Data Index: 740116 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0699. Min Act: -0.0005

Data Index: 888052 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0700. Min Act: -0.0005

Data Index: 179467 (C4 (Web Text))

Max Activating Token Index: 301