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

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

Neuron 630 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1171. Min Act: -0.0003

Data Index: 132640 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0976. Min Act: -0.0003

Data Index: 1250111 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0934. Min Act: -0.0003

Data Index: 327468 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0964. Min Act: -0.0003

Data Index: 825508 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0914. Min Act: -0.0003

Data Index: 666735 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.1071. Min Act: -0.0003

Data Index: 779626 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0996. Min Act: -0.0003

Data Index: 1117285 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0894. Min Act: -0.0003

Data Index: 304994 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0842. Min Act: -0.0003

Data Index: 922790 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0881. Min Act: -0.0003

Data Index: 607902 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0962. Min Act: -0.0003

Data Index: 1281301 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0844. Min Act: -0.0003

Data Index: 473798 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0898. Min Act: -0.0003

Data Index: 242609 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0827. Min Act: -0.0003

Data Index: 995753 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0816. Min Act: -0.0003

Data Index: 981224 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1340674 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0908. Min Act: -0.0003

Data Index: 909213 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0824. Min Act: -0.0003

Data Index: 1046976 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0837. Min Act: -0.0003

Data Index: 835322 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.1171. Min Range: -0.1171

Max Act: 0.0782. Min Act: -0.0003

Data Index: 813440 (C4 (Web Text))

Max Activating Token Index: 976