Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3488 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1496914 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1482692 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5871. Min Act: -0.0000

Data Index: 90519 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1634990 (Python Code)

Max Activating Token Index: 509

Text #4

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5783. Min Act: -0.0000

Data Index: 608288 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1416136 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4902. Min Act: -0.0000

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5364. Min Act: -0.0000

Data Index: 388108 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1515729 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1585280 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1627229 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4945. Min Act: 0.0000

Data Index: 38344 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1455223 (Python Code)

Max Activating Token Index: 298

Text #13

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1544748 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4775. Min Act: -0.0000

Data Index: 206780 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1482923 (Python Code)

Max Activating Token Index: 944

Text #16

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4763. Min Act: 0.0000

Data Index: 1324974 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4507. Min Act: -0.0000

Data Index: 725968 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1638982 (Python Code)

Max Activating Token Index: 538

Text #19

Max Range: 0.6049. Min Range: -0.6049

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1234414 (C4 (Web Text))

Max Activating Token Index: 286