Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 142 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2012. Min Act: -0.0001

Data Index: 802113 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.2096. Min Act: -0.0001

Data Index: 1391039 (Python Code)

Max Activating Token Index: 660

Text #2

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1906. Min Act: -0.0001

Data Index: 1176624 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1892. Min Act: -0.0001

Data Index: 1651707 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1460263 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1777. Min Act: -0.0001

Data Index: 674291 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1793. Min Act: -0.0001

Data Index: 471150 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1723. Min Act: -0.0001

Data Index: 173969 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1576158 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1648. Min Act: -0.0001

Data Index: 694282 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1586. Min Act: -0.0001

Data Index: 1356949 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1518822 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1575. Min Act: -0.0001

Data Index: 463686 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1560. Min Act: 0.0000

Data Index: 1369223 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1454681 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1038298 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1626. Min Act: -0.0001

Data Index: 324440 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1609. Min Act: -0.0001

Data Index: 839 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1609. Min Act: -0.0001

Data Index: 922862 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.2096. Min Range: -0.2096

Max Act: 0.1539. Min Act: -0.0001

Data Index: 288665 (C4 (Web Text))

Max Activating Token Index: 744