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

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

Neuron 3357 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2613. Min Act: -0.0001

Data Index: 191600 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2435. Min Act: -0.0001

Data Index: 17672 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.2102. Min Act: -0.0001

Data Index: 1280326 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1128379 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1898. Min Act: -0.0001

Data Index: 417512 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1915. Min Act: -0.0001

Data Index: 60256 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1862. Min Act: -0.0001

Data Index: 508500 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1513. Min Act: -0.0001

Data Index: 1336 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1737. Min Act: -0.0001

Data Index: 392529 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1813. Min Act: -0.0001

Data Index: 929166 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1752. Min Act: -0.0001

Data Index: 26011 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1708. Min Act: -0.0001

Data Index: 583784 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1684. Min Act: -0.0001

Data Index: 636625 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1743. Min Act: -0.0001

Data Index: 118113 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1105677 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1033941 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1597. Min Act: -0.0001

Data Index: 382504 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1586. Min Act: -0.0001

Data Index: 552358 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1299662 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.2613. Min Range: -0.2613

Max Act: 0.1672. Min Act: -0.0001

Data Index: 880709 (C4 (Web Text))

Max Activating Token Index: 573