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

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

Neuron 1048 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: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0005

Data Index: 100680 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0695. Min Act: -0.0005

Data Index: 98886 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0649. Min Act: -0.0004

Data Index: 763005 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0628. Min Act: -0.0005

Data Index: 75880 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0572. Min Act: -0.0005

Data Index: 466008 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0578. Min Act: -0.0005

Data Index: 270253 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0567. Min Act: -0.0005

Data Index: 756988 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0604. Min Act: -0.0005

Data Index: 190917 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0585. Min Act: -0.0005

Data Index: 415664 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0607. Min Act: -0.0005

Data Index: 1006155 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0595. Min Act: -0.0005

Data Index: 428212 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0593. Min Act: -0.0005

Data Index: 853254 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0608. Min Act: -0.0005

Data Index: 1060448 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0592. Min Act: -0.0005

Data Index: 444507 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0600. Min Act: -0.0005

Data Index: 247070 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0556. Min Act: -0.0005

Data Index: 1097821 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0581. Min Act: -0.0005

Data Index: 51118 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0529. Min Act: -0.0005

Data Index: 645513 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0565. Min Act: -0.0005

Data Index: 1081568 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0563. Min Act: -0.0005

Data Index: 362638 (C4 (Web Text))

Max Activating Token Index: 95