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

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

Neuron 4155 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1566272 (Python Code)

Max Activating Token Index: 394

Text #1

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1557529 (Python Code)

Max Activating Token Index: 356

Text #2

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.1273. Min Act: -0.0000

Data Index: 1395929 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1372267 (Python Code)

Max Activating Token Index: 651

Text #4

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1516346 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0595. Min Act: -0.0001

Data Index: 1382910 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1397501 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1560904 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 1.1695. Min Range: -1.1695

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1435996 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9873. Min Act: -0.0000

Data Index: 884283 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1553585 (Python Code)

Max Activating Token Index: 290

Text #11

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9852. Min Act: -0.0000

Data Index: 1583055 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1498867 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1361876 (Python Code)

Max Activating Token Index: 388

Text #14

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1652005 (Python Code)

Max Activating Token Index: 915

Text #15

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9323. Min Act: -0.0001

Data Index: 1575582 (Python Code)

Max Activating Token Index: 690

Text #16

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1615426 (Python Code)

Max Activating Token Index: 189

Text #17

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1429593 (Python Code)

Max Activating Token Index: 457

Text #18

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1457285 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 1.1695. Min Range: -1.1695

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1431396 (Python Code)

Max Activating Token Index: 589