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

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

Neuron 2027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1637265 (Python Code)

Max Activating Token Index: 17

Text #1

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0862. Min Act: -0.0001

Data Index: 215298 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1560141 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0806. Min Act: -0.0001

Data Index: 990612 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0629. Min Act: -0.0001

Data Index: 144490 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0730. Min Act: -0.0001

Data Index: 620398 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1068745 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0673. Min Act: -0.0001

Data Index: 245603 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0725. Min Act: -0.0000

Data Index: 1048583 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0600. Min Act: -0.0001

Data Index: 499923 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0627. Min Act: -0.0000

Data Index: 358189 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0672. Min Act: -0.0001

Data Index: 29311 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0644. Min Act: -0.0001

Data Index: 882993 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0668. Min Act: -0.0000

Data Index: 314125 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0634. Min Act: -0.0001

Data Index: 641337 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1061220 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1588303 (Python Code)

Max Activating Token Index: 941

Text #17

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0621. Min Act: -0.0001

Data Index: 610299 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1617045 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.0892. Min Range: -0.0892

Max Act: 0.0639. Min Act: -0.0001

Data Index: 567527 (C4 (Web Text))

Max Activating Token Index: 28