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

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

Neuron 1396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0780. Min Act: -0.0004

Data Index: 1425 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0592. Min Act: -0.0004

Data Index: 767942 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0616. Min Act: -0.0004

Data Index: 553371 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0588. Min Act: -0.0004

Data Index: 75202 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0683. Min Act: -0.0004

Data Index: 864624 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0650. Min Act: -0.0004

Data Index: 734301 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0756. Min Act: -0.0004

Data Index: 102576 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0733. Min Act: -0.0004

Data Index: 295631 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0623. Min Act: -0.0004

Data Index: 43182 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0610. Min Act: -0.0004

Data Index: 1158273 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0586. Min Act: -0.0004

Data Index: 1041469 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0604. Min Act: -0.0004

Data Index: 265712 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0667. Min Act: -0.0004

Data Index: 292922 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0533. Min Act: -0.0004

Data Index: 721690 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0552. Min Act: -0.0004

Data Index: 750121 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0512. Min Act: -0.0004

Data Index: 96692 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0632. Min Act: -0.0004

Data Index: 1334704 (C4 (Web Text))

Max Activating Token Index: 600

Text #17

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0544. Min Act: -0.0004

Data Index: 500868 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0580. Min Act: -0.0004

Data Index: 1296862 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0780. Min Range: -0.0780

Max Act: 0.0587. Min Act: -0.0004

Data Index: 864893 (C4 (Web Text))

Max Activating Token Index: 955