Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4663 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0000

Data Index: 732782 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1607637 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1423115 (Python Code)

Max Activating Token Index: 943

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0868. Min Act: -0.0000

Data Index: 484097 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1042694 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0839. Min Act: -0.0000

Data Index: 901617 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0764. Min Act: -0.0000

Data Index: 203981 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1375727 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1317319 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0767. Min Act: -0.0000

Data Index: 894659 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1093501 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1538806 (Python Code)

Max Activating Token Index: 736

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0795. Min Act: -0.0000

Data Index: 775521 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0755. Min Act: -0.0000

Data Index: 147017 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1537031 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0727. Min Act: -0.0000

Data Index: 119361 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0705. Min Act: -0.0000

Data Index: 999871 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0686. Min Act: -0.0000

Data Index: 62452 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1405002 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0704. Min Act: -0.0000

Data Index: 217908 (C4 (Web Text))

Max Activating Token Index: 441