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

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

Neuron 2302 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: 0.2100. Min Range: -0.2100

Max Act: 0.2100. Min Act: -0.0001

Data Index: 1026834 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1903. Min Act: -0.0001

Data Index: 697129 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1921. Min Act: -0.0001

Data Index: 253341 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1872. Min Act: -0.0001

Data Index: 786109 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1813. Min Act: -0.0001

Data Index: 731893 (C4 (Web Text))

Max Activating Token Index: 485

Text #5

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1059457 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1780. Min Act: -0.0001

Data Index: 374396 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1341351 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1748. Min Act: -0.0001

Data Index: 256654 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1610. Min Act: -0.0001

Data Index: 94060 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1221192 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1690. Min Act: -0.0001

Data Index: 239495 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1093118 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1675. Min Act: -0.0001

Data Index: 604053 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1650. Min Act: -0.0001

Data Index: 549273 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1581. Min Act: -0.0001

Data Index: 722832 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1606. Min Act: -0.0001

Data Index: 421651 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1555. Min Act: -0.0001

Data Index: 292378 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1138587 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1102849 (C4 (Web Text))

Max Activating Token Index: 196