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

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

Neuron 4525 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1127. Min Act: -0.0002

Data Index: 683330 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1058. Min Act: -0.0002

Data Index: 802688 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1006. Min Act: -0.0002

Data Index: 872441 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0996. Min Act: -0.0002

Data Index: 677513 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0925. Min Act: -0.0002

Data Index: 420360 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1500032 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0948. Min Act: -0.0002

Data Index: 765480 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1119004 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0880. Min Act: -0.0002

Data Index: 749762 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0911. Min Act: -0.0002

Data Index: 369367 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1026756 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1224128 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1629929 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1118343 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1598119 (Python Code)

Max Activating Token Index: 674

Text #15

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1640036 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1645623 (Python Code)

Max Activating Token Index: 655

Text #17

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0879. Min Act: -0.0002

Data Index: 154877 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0874. Min Act: -0.0002

Data Index: 43875 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1489984 (Python Code)

Max Activating Token Index: 721