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

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

Neuron 2175 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1312358 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.2064. Min Act: -0.0000

Data Index: 654380 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1877. Min Act: -0.0000

Data Index: 139369 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1858. Min Act: -0.0000

Data Index: 353983 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1851. Min Act: -0.0000

Data Index: 102683 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1855. Min Act: -0.0000

Data Index: 658271 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1833. Min Act: -0.0000

Data Index: 370608 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1163705 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1755. Min Act: -0.0000

Data Index: 986675 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1477846 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1090555 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1009531 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1116365 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1593684 (Python Code)

Max Activating Token Index: 1006

Text #14

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1776. Min Act: -0.0000

Data Index: 5748 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1780. Min Act: -0.0000

Data Index: 471457 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1060635 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1619296 (Python Code)

Max Activating Token Index: 428

Text #18

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1641. Min Act: -0.0000

Data Index: 501155 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.2064. Min Range: -0.2064

Max Act: 0.1749. Min Act: -0.0000

Data Index: 285788 (C4 (Web Text))

Max Activating Token Index: 26