Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5060 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2754. Min Act: -0.0001

Data Index: 1149494 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1145235 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2199. Min Act: -0.0000

Data Index: 225265 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2190. Min Act: -0.0000

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1869. Min Act: -0.0000

Data Index: 37605 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2007. Min Act: -0.0001

Data Index: 554221 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2038. Min Act: -0.0001

Data Index: 261265 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1219590 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1199441 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1728. Min Act: -0.0000

Data Index: 700448 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1739. Min Act: -0.0000

Data Index: 823936 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1358094 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1640. Min Act: -0.0001

Data Index: 863690 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1686. Min Act: -0.0000

Data Index: 609589 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1692. Min Act: -0.0000

Data Index: 1344205 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1809. Min Act: -0.0000

Data Index: 353342 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1690. Min Act: -0.0000

Data Index: 507582 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1599. Min Act: -0.0000

Data Index: 501631 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1245594 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1280799 (C4 (Web Text))

Max Activating Token Index: 347