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

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

Neuron 3309 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.1066. Min Act: -0.0001

Data Index: 591551 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0978. Min Act: -0.0001

Data Index: 950300 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0966. Min Act: -0.0002

Data Index: 287576 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1223290 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0959. Min Act: -0.0001

Data Index: 418449 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0891. Min Act: -0.0002

Data Index: 507605 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0839. Min Act: -0.0001

Data Index: 594551 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0862. Min Act: -0.0002

Data Index: 339670 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0857. Min Act: -0.0001

Data Index: 775669 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0853. Min Act: -0.0001

Data Index: 474550 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1597061 (Python Code)

Max Activating Token Index: 750

Text #11

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0870. Min Act: -0.0001

Data Index: 348876 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0858. Min Act: -0.0002

Data Index: 340521 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1264299 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1136840 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0840. Min Act: -0.0001

Data Index: 765191 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0846. Min Act: -0.0002

Data Index: 373240 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0842. Min Act: -0.0002

Data Index: 533246 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0869. Min Act: -0.0002

Data Index: 864501 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.1066. Min Range: -0.1066

Max Act: 0.0842. Min Act: -0.0001

Data Index: 642517 (C4 (Web Text))

Max Activating Token Index: 389