Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1468 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2995. Min Act: -0.0000

Data Index: 630891 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2515. Min Act: -0.0000

Data Index: 165330 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1177911 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2050. Min Act: -0.0000

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2048. Min Act: -0.0000

Data Index: 730515 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1891. Min Act: -0.0000

Data Index: 635581 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.2033. Min Act: -0.0000

Data Index: 856993 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1930. Min Act: -0.0001

Data Index: 1156328 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1725. Min Act: -0.0001

Data Index: 789260 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1859. Min Act: -0.0001

Data Index: 599934 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1935. Min Act: -0.0001

Data Index: 275744 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1767. Min Act: -0.0000

Data Index: 146347 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1935. Min Act: -0.0000

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1787. Min Act: -0.0000

Data Index: 473064 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1833. Min Act: -0.0001

Data Index: 322813 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1753. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1761. Min Act: -0.0000

Data Index: 753198 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1745. Min Act: -0.0000

Data Index: 403640 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.2995. Min Range: -0.2995

Max Act: 0.1803. Min Act: -0.0000

Data Index: 135466 (C4 (Web Text))

Max Activating Token Index: 857