Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2768 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.3604. Min Act: -0.0001

Data Index: 5669 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.2149. Min Act: -0.0001

Data Index: 1466721 (Python Code)

Max Activating Token Index: 354

Text #2

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1757. Min Act: -0.0001

Data Index: 1627105 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0519. Min Act: -0.0001

Data Index: 1360830 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1333. Min Act: -0.0001

Data Index: 1590996 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1399. Min Act: -0.0001

Data Index: 1432221 (Python Code)

Max Activating Token Index: 659

Text #6

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1622. Min Act: -0.0001

Data Index: 1636322 (Python Code)

Max Activating Token Index: 155

Text #7

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1102. Min Act: -0.0001

Data Index: 881670 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1443157 (Python Code)

Max Activating Token Index: 145

Text #9

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.2007. Min Act: -0.0001

Data Index: 1606480 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0988. Min Act: -0.0001

Data Index: 1408627 (Python Code)

Max Activating Token Index: 718

Text #11

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0117. Min Act: -0.0001

Data Index: 168611 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1614. Min Act: -0.0001

Data Index: 1222089 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0854. Min Act: -0.0001

Data Index: 1572392 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0300. Min Act: -0.0001

Data Index: 1425023 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0663. Min Act: -0.0001

Data Index: 465291 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1409891 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1406. Min Act: -0.0001

Data Index: 1611558 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1329. Min Act: -0.0001

Data Index: 1448705 (Python Code)

Max Activating Token Index: 258

Text #19

Max Range: 1.3604. Min Range: -1.3604

Max Act: 1.1666. Min Act: -0.0001

Data Index: 1442074 (Python Code)

Max Activating Token Index: 147