Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3882. Min Act: -0.0000

Data Index: 594427 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3723. Min Act: -0.0001

Data Index: 800546 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3196. Min Act: -0.0000

Data Index: 880362 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3364. Min Act: -0.0000

Data Index: 843635 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3359. Min Act: -0.0000

Data Index: 346099 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3195. Min Act: -0.0000

Data Index: 669552 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3149. Min Act: -0.0001

Data Index: 662041 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3141. Min Act: -0.0000

Data Index: 528982 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3261. Min Act: -0.0001

Data Index: 905557 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3187. Min Act: -0.0001

Data Index: 1093896 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2834. Min Act: -0.0001

Data Index: 232803 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3261. Min Act: -0.0001

Data Index: 313409 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3015. Min Act: -0.0001

Data Index: 236958 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3035. Min Act: -0.0001

Data Index: 979409 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2701. Min Act: -0.0001

Data Index: 1038921 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2692. Min Act: -0.0001

Data Index: 1318948 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1252319 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2900. Min Act: -0.0001

Data Index: 668860 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.3011. Min Act: -0.0001

Data Index: 241713 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.3882. Min Range: -0.3882

Max Act: 0.2868. Min Act: -0.0000

Data Index: 1282714 (C4 (Web Text))

Max Activating Token Index: 62