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

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

Neuron 4783 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0234. Min Range: -2.0234

Max Act: 2.0234. Min Act: -0.0000

Data Index: 1236045 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.6536. Min Act: -0.0000

Data Index: 75747 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1051612 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.6247. Min Act: -0.0000

Data Index: 872355 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.6042. Min Act: -0.0000

Data Index: 1519414 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1384514 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.4374. Min Act: -0.0000

Data Index: 1052483 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.5917. Min Act: -0.0000

Data Index: 463823 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.4768. Min Act: -0.0000

Data Index: 657283 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1472530 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.4642. Min Act: -0.0000

Data Index: 1136709 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.5939. Min Act: -0.0000

Data Index: 1392639 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.5289. Min Act: -0.0000

Data Index: 1546891 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.4234. Min Act: -0.0000

Data Index: 744478 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.3730. Min Act: -0.0000

Data Index: 1490894 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.3975. Min Act: -0.0000

Data Index: 555731 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.3900. Min Act: -0.0000

Data Index: 396794 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1081670 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.4603. Min Act: -0.0000

Data Index: 674629 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 2.0234. Min Range: -2.0234

Max Act: 1.3734. Min Act: -0.0000

Data Index: 1633928 (Python Code)

Max Activating Token Index: 590