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

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

Neuron 2735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1619349 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5794. Min Act: -0.0000

Data Index: 1546599 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1508881 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1627233 (Python Code)

Max Activating Token Index: 492

Text #4

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1364212 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1484873 (Python Code)

Max Activating Token Index: 427

Text #6

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1652384 (Python Code)

Max Activating Token Index: 946

Text #7

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1560312 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1395020 (Python Code)

Max Activating Token Index: 997

Text #9

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1595101 (Python Code)

Max Activating Token Index: 359

Text #10

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1583959 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1361243 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1628481 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1516885 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1403678 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1656011 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1439328 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1592794 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1599215 (Python Code)

Max Activating Token Index: 299

Text #19

Max Range: 0.6829. Min Range: -0.6829

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1619734 (Python Code)

Max Activating Token Index: 298