Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1768 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1109935 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1012317 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0857. Min Act: -0.0002

Data Index: 797752 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1009454 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1292658 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0792. Min Act: -0.0002

Data Index: 712333 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1274738 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1180418 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1183806 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0775. Min Act: -0.0002

Data Index: 982947 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0756. Min Act: -0.0002

Data Index: 562015 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0775. Min Act: -0.0002

Data Index: 383670 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1211852 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0764. Min Act: -0.0001

Data Index: 31202 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0787. Min Act: -0.0002

Data Index: 817475 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0759. Min Act: -0.0002

Data Index: 49237 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1093732 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0729. Min Act: -0.0002

Data Index: 636181 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1042837 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0725. Min Act: -0.0002

Data Index: 293303 (C4 (Web Text))

Max Activating Token Index: 962