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

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

Neuron 3030 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: 0.2106. Min Range: -0.2106

Max Act: 0.1976. Min Act: -0.0001

Data Index: 654724 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.2106. Min Act: -0.0001

Data Index: 641681 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1910. Min Act: -0.0001

Data Index: 128319 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1909. Min Act: -0.0001

Data Index: 77625 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1867. Min Act: -0.0001

Data Index: 705836 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1714. Min Act: -0.0001

Data Index: 432520 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1798. Min Act: -0.0001

Data Index: 347024 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1330000 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1681. Min Act: -0.0001

Data Index: 173386 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1204447 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1730. Min Act: -0.0001

Data Index: 199617 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1316228 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1641. Min Act: -0.0001

Data Index: 886998 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1639. Min Act: -0.0001

Data Index: 797894 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1190290 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1569. Min Act: -0.0001

Data Index: 664073 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1726. Min Act: -0.0001

Data Index: 74014 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1597. Min Act: -0.0001

Data Index: 247473 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1700. Min Act: -0.0001

Data Index: 459055 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.2106. Min Range: -0.2106

Max Act: 0.1627. Min Act: -0.0001

Data Index: 173494 (C4 (Web Text))

Max Activating Token Index: 156