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

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

Neuron 3187 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: 0.0857. Min Range: -0.0857

Max Act: 0.0836. Min Act: -0.0002

Data Index: 640694 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0799. Min Act: -0.0002

Data Index: 925486 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1590152 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0778. Min Act: -0.0001

Data Index: 732398 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0816. Min Act: -0.0001

Data Index: 577090 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1029863 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1340690 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0825. Min Act: -0.0002

Data Index: 399628 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1564728 (Python Code)

Max Activating Token Index: 194

Text #9

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0718. Min Act: -0.0002

Data Index: 112904 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1205019 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0721. Min Act: -0.0001

Data Index: 936146 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1476020 (Python Code)

Max Activating Token Index: 395

Text #13

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0790. Min Act: -0.0002

Data Index: 586319 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1603433 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1380613 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0710. Min Act: -0.0002

Data Index: 261698 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0730. Min Act: -0.0002

Data Index: 289421 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0645. Min Act: -0.0002

Data Index: 41942 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0857. Min Range: -0.0857

Max Act: 0.0699. Min Act: -0.0002

Data Index: 38784 (C4 (Web Text))

Max Activating Token Index: 468