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

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

Neuron 4033 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0002

Data Index: 952733 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0772. Min Act: -0.0002

Data Index: 931756 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0788. Min Act: -0.0002

Data Index: 338745 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0746. Min Act: -0.0002

Data Index: 603041 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1194450 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0712. Min Act: -0.0002

Data Index: 371763 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1082829 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0694. Min Act: -0.0002

Data Index: 632093 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0728. Min Act: -0.0002

Data Index: 396677 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0666. Min Act: -0.0002

Data Index: 328092 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1130915 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0712. Min Act: -0.0002

Data Index: 464964 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1042151 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0588. Min Act: -0.0002

Data Index: 823605 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0652. Min Act: -0.0002

Data Index: 709916 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0671. Min Act: -0.0002

Data Index: 148021 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1167504 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0643. Min Act: -0.0002

Data Index: 847542 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0647. Min Act: -0.0002

Data Index: 456452 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0690. Min Act: -0.0002

Data Index: 324555 (C4 (Web Text))

Max Activating Token Index: 418