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

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

Neuron 585 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1892. Min Act: -0.0001

Data Index: 907886 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1786. Min Act: -0.0001

Data Index: 313912 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1765. Min Act: -0.0001

Data Index: 991233 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1224304 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1741. Min Act: -0.0001

Data Index: 631442 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1694. Min Act: -0.0001

Data Index: 282048 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1329120 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1653. Min Act: -0.0001

Data Index: 225933 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1582. Min Act: -0.0001

Data Index: 22457 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1627. Min Act: -0.0001

Data Index: 275610 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1673. Min Act: -0.0001

Data Index: 309234 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1791. Min Act: -0.0001

Data Index: 487506 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1096558 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1201108 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1528. Min Act: -0.0001

Data Index: 33565 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1585. Min Act: -0.0001

Data Index: 343467 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1563. Min Act: -0.0001

Data Index: 280333 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1323595 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1455. Min Act: -0.0001

Data Index: 300670 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.1892. Min Range: -0.1892

Max Act: 0.1536. Min Act: -0.0001

Data Index: 328705 (C4 (Web Text))

Max Activating Token Index: 744