Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0001

Data Index: 429022 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0740. Min Act: -0.0001

Data Index: 183873 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0796. Min Act: -0.0001

Data Index: 957907 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0750. Min Act: -0.0001

Data Index: 372295 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1302549 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0773. Min Act: -0.0001

Data Index: 139624 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1155634 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1096039 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0723. Min Act: -0.0001

Data Index: 843164 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0749. Min Act: -0.0001

Data Index: 337077 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0717. Min Act: -0.0001

Data Index: 865449 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0697. Min Act: -0.0001

Data Index: 625119 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0756. Min Act: -0.0001

Data Index: 406368 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0681. Min Act: -0.0001

Data Index: 278816 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0681. Min Act: -0.0001

Data Index: 240924 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0746. Min Act: -0.0001

Data Index: 641706 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0725. Min Act: -0.0001

Data Index: 295775 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0713. Min Act: -0.0001

Data Index: 396140 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0791. Min Act: -0.0001

Data Index: 823107 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0702. Min Act: -0.0001

Data Index: 971708 (C4 (Web Text))

Max Activating Token Index: 890