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

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

Neuron 48 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: 0.1055. Min Range: -0.1055

Max Act: 0.1033. Min Act: -0.0000

Data Index: 649110 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1001. Min Act: -0.0000

Data Index: 91248 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.1055. Min Act: -0.0000

Data Index: 802797 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0948. Min Act: -0.0000

Data Index: 277766 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1272538 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0894. Min Act: -0.0000

Data Index: 65756 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0922. Min Act: -0.0001

Data Index: 768419 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0911. Min Act: -0.0001

Data Index: 653901 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0915. Min Act: -0.0001

Data Index: 574457 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0995. Min Act: -0.0000

Data Index: 190579 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1271650 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0807. Min Act: -0.0000

Data Index: 653854 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0829. Min Act: -0.0000

Data Index: 543854 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0954. Min Act: -0.0000

Data Index: 171118 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0838. Min Act: -0.0000

Data Index: 660837 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0839. Min Act: -0.0000

Data Index: 334944 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0889. Min Act: -0.0000

Data Index: 999931 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1146875 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0744. Min Act: -0.0000

Data Index: 662946 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.1055. Min Range: -0.1055

Max Act: 0.0718. Min Act: -0.0000

Data Index: 375692 (C4 (Web Text))

Max Activating Token Index: 509