Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4879 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1494852 (Python Code)

Max Activating Token Index: 1016

Text #1

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1621657 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1033959 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1048151 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3048. Min Act: -0.0000

Data Index: 435087 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1649373 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1304818 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1541115 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1142326 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1499821 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2897. Min Act: -0.0000

Data Index: 121944 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1403438 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2885. Min Act: -0.0000

Data Index: 830812 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2558. Min Act: -0.0000

Data Index: 169670 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2737. Min Act: -0.0000

Data Index: 839722 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2609. Min Act: -0.0000

Data Index: 750759 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1086663 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2726. Min Act: -0.0000

Data Index: 973888 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1023913 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.5754. Min Range: -0.5754

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1569601 (Python Code)

Max Activating Token Index: 791