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

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

Neuron 1732 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: 1.5612. Min Range: -1.5612

Max Act: 1.5612. Min Act: -0.0002

Data Index: 911154 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.3602. Min Act: -0.0002

Data Index: 957557 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.2130. Min Act: -0.0002

Data Index: 592859 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.2189. Min Act: -0.0002

Data Index: 741968 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.2594. Min Act: -0.0002

Data Index: 1316086 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.1095. Min Act: -0.0002

Data Index: 1243377 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0303. Min Act: -0.0002

Data Index: 911794 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0949. Min Act: -0.0002

Data Index: 498975 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.1965. Min Act: -0.0002

Data Index: 509728 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0294. Min Act: -0.0002

Data Index: 1196175 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0293. Min Act: -0.0002

Data Index: 671917 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0865. Min Act: -0.0002

Data Index: 402624 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.5612. Min Range: -1.5612

Max Act: 0.9565. Min Act: -0.0002

Data Index: 674504 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.2079. Min Act: -0.0002

Data Index: 222929 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 1.5612. Min Range: -1.5612

Max Act: 0.9780. Min Act: -0.0002

Data Index: 728163 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.5612. Min Range: -1.5612

Max Act: 0.9752. Min Act: -0.0002

Data Index: 1163543 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0930. Min Act: -0.0002

Data Index: 523229 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0721. Min Act: -0.0002

Data Index: 663202 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 1.5612. Min Range: -1.5612

Max Act: 1.0606. Min Act: -0.0002

Data Index: 219590 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 1.5612. Min Range: -1.5612

Max Act: 0.9988. Min Act: -0.0002

Data Index: 16838 (C4 (Web Text))

Max Activating Token Index: 317