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

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

Neuron 114 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.2106. Min Act: -0.0001

Data Index: 44405 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.2009. Min Act: -0.0001

Data Index: 777835 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.2082. Min Act: -0.0001

Data Index: 861129 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.2006. Min Act: -0.0001

Data Index: 536679 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.2064. Min Act: -0.0001

Data Index: 946244 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1844. Min Act: -0.0001

Data Index: 588463 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1758. Min Act: -0.0001

Data Index: 939585 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1751. Min Act: -0.0001

Data Index: 128071 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1854. Min Act: -0.0001

Data Index: 246804 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1915. Min Act: -0.0001

Data Index: 301138 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1854. Min Act: -0.0001

Data Index: 1014177 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1746. Min Act: -0.0000

Data Index: 1335306 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1812. Min Act: -0.0001

Data Index: 405353 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1945. Min Act: -0.0001

Data Index: 774851 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1741. Min Act: -0.0001

Data Index: 467709 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1276559 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1782. Min Act: -0.0001

Data Index: 145698 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1834. Min Act: -0.0001

Data Index: 503429 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1699. Min Act: -0.0001

Data Index: 109982 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1750. Min Act: -0.0001

Data Index: 227050 (C4 (Web Text))

Max Activating Token Index: 493