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

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

Neuron 3948 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: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0002

Data Index: 88372 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0934. Min Act: -0.0001

Data Index: 466709 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1610888 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1258341 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0850. Min Act: -0.0001

Data Index: 789916 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0772. Min Act: -0.0001

Data Index: 604969 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0857. Min Act: -0.0002

Data Index: 742565 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0791. Min Act: -0.0001

Data Index: 562294 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0830. Min Act: -0.0002

Data Index: 886709 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0783. Min Act: -0.0002

Data Index: 249393 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0808. Min Act: -0.0002

Data Index: 572549 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0779. Min Act: -0.0002

Data Index: 667560 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0786. Min Act: -0.0002

Data Index: 14129 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0775. Min Act: -0.0001

Data Index: 448875 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1650668 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0796. Min Act: -0.0002

Data Index: 822509 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1387998 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0736. Min Act: -0.0002

Data Index: 96504 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1268361 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1571852 (Python Code)

Max Activating Token Index: 47