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

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

Neuron 2670 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.1001. Min Act: -0.0001

Data Index: 309966 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0945. Min Act: -0.0001

Data Index: 377333 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0936. Min Act: -0.0001

Data Index: 262461 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1245073 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0836. Min Act: -0.0001

Data Index: 200024 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0875. Min Act: -0.0001

Data Index: 794408 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0832. Min Act: -0.0001

Data Index: 717266 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1094556 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0861. Min Act: -0.0001

Data Index: 353324 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0850. Min Act: -0.0001

Data Index: 884446 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1130296 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1103805 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0855. Min Act: -0.0001

Data Index: 427672 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0815. Min Act: -0.0001

Data Index: 332644 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0753. Min Act: -0.0001

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0787. Min Act: -0.0001

Data Index: 891330 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1247526 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0772. Min Act: -0.0001

Data Index: 440429 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0795. Min Act: -0.0001

Data Index: 196740 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1001. Min Range: -0.1001

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 803