Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 675 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1034. Min Act: -0.0001

Data Index: 419529 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0944. Min Act: -0.0001

Data Index: 208706 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1075265 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1219434 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0781. Min Act: -0.0001

Data Index: 931856 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0001

Data Index: 391897 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0841. Min Act: -0.0001

Data Index: 851595 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0852. Min Act: -0.0001

Data Index: 385860 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0774. Min Act: -0.0001

Data Index: 834383 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0818. Min Act: -0.0001

Data Index: 261685 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0811. Min Act: -0.0001

Data Index: 32071 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1279236 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0838. Min Act: -0.0001

Data Index: 910400 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0801. Min Act: -0.0001

Data Index: 878567 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0707. Min Act: -0.0001

Data Index: 980861 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0800. Min Act: -0.0001

Data Index: 733552 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0777. Min Act: -0.0001

Data Index: 601647 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0729. Min Act: -0.0001

Data Index: 414488 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1452350 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0820. Min Act: -0.0001

Data Index: 78281 (C4 (Web Text))

Max Activating Token Index: 456