Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3653 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0001

Data Index: 537748 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1047. Min Act: -0.0000

Data Index: 206413 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1011. Min Act: -0.0000

Data Index: 513752 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0959. Min Act: -0.0000

Data Index: 849765 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0976. Min Act: -0.0000

Data Index: 523977 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0939. Min Act: -0.0001

Data Index: 989278 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0870. Min Act: -0.0000

Data Index: 675836 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0861. Min Act: -0.0000

Data Index: 612053 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0892. Min Act: -0.0000

Data Index: 868075 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0884. Min Act: -0.0000

Data Index: 486416 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0954. Min Act: -0.0001

Data Index: 449884 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0869. Min Act: -0.0001

Data Index: 210327 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0814. Min Act: -0.0000

Data Index: 968105 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0807. Min Act: -0.0000

Data Index: 207725 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1301778 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0804. Min Act: -0.0000

Data Index: 995235 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0823. Min Act: -0.0000

Data Index: 36572 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1172090 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0808. Min Act: -0.0001

Data Index: 954081 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0835. Min Act: -0.0000

Data Index: 506836 (C4 (Web Text))

Max Activating Token Index: 379