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

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

Neuron 4968 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: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0002

Data Index: 677936 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1391878 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1129153 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0554. Min Act: -0.0002

Data Index: 677841 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0588. Min Act: -0.0002

Data Index: 374222 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0563. Min Act: -0.0002

Data Index: 11933 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1652858 (Python Code)

Max Activating Token Index: 634

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0526. Min Act: -0.0002

Data Index: 117123 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0474. Min Act: -0.0002

Data Index: 919858 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0516. Min Act: -0.0002

Data Index: 363788 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0450. Min Act: -0.0002

Data Index: 513326 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0455. Min Act: -0.0002

Data Index: 885403 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1060033 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0446. Min Act: -0.0002

Data Index: 506108 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1047358 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0469. Min Act: -0.0002

Data Index: 33776 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0394. Min Act: -0.0002

Data Index: 395387 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1003064 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0350. Min Act: -0.0002

Data Index: 715833 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0450. Min Act: -0.0002

Data Index: 982735 (C4 (Web Text))

Max Activating Token Index: 8