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

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

Neuron 1342 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1867. Min Act: -0.0000

Data Index: 425540 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1857. Min Act: -0.0000

Data Index: 188013 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1856. Min Act: -0.0000

Data Index: 237499 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1147787 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1098154 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1304426 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1302840 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1710. Min Act: -0.0000

Data Index: 793409 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1285276 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1123720 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1290945 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1585. Min Act: -0.0000

Data Index: 298590 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1347022 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1605. Min Act: -0.0001

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1334323 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1094183 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1456. Min Act: -0.0000

Data Index: 394974 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1653. Min Act: -0.0001

Data Index: 332957 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1554. Min Act: -0.0001

Data Index: 940313 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1003305 (C4 (Web Text))

Max Activating Token Index: 492