Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 930 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1913. Min Act: -0.0004

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1698. Min Act: -0.0004

Data Index: 1159197 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1747. Min Act: -0.0004

Data Index: 231618 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1686. Min Act: -0.0004

Data Index: 46138 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1734. Min Act: -0.0004

Data Index: 1201593 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1722. Min Act: -0.0004

Data Index: 93513 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1655. Min Act: -0.0004

Data Index: 391596 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1665. Min Act: -0.0004

Data Index: 1315131 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1653. Min Act: -0.0004

Data Index: 156912 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1770. Min Act: -0.0004

Data Index: 188244 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1688. Min Act: -0.0004

Data Index: 895574 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1690. Min Act: -0.0004

Data Index: 1288816 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1558. Min Act: -0.0004

Data Index: 402167 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1687. Min Act: -0.0004

Data Index: 1259849 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1627. Min Act: -0.0004

Data Index: 347816 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1610. Min Act: -0.0004

Data Index: 835718 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1608. Min Act: -0.0004

Data Index: 1179420 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1612. Min Act: -0.0004

Data Index: 164726 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1597. Min Act: -0.0004

Data Index: 486964 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.1913. Min Range: -0.1913

Max Act: 0.1550. Min Act: -0.0004

Data Index: 1244394 (C4 (Web Text))

Max Activating Token Index: 658