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

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

Neuron 1427 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2137. Min Act: -0.0001

Data Index: 146885 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1991. Min Act: -0.0000

Data Index: 559293 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2024. Min Act: -0.0001

Data Index: 1654617 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1128758 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1308753 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1370125 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1931. Min Act: -0.0000

Data Index: 863252 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1779. Min Act: -0.0000

Data Index: 780204 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1881. Min Act: -0.0000

Data Index: 605447 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1303822 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1363775 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1407414 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1686. Min Act: -0.0001

Data Index: 870701 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1592846 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1445258 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1362471 (Python Code)

Max Activating Token Index: 697

Text #17

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1580. Min Act: -0.0001

Data Index: 94060 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1601. Min Act: -0.0001

Data Index: 909118 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.2137. Min Range: -0.2137

Max Act: 0.1494. Min Act: -0.0000

Data Index: 648323 (C4 (Web Text))

Max Activating Token Index: 162