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

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

Neuron 1468 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2754. Min Act: -0.0001

Data Index: 1141336 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2639. Min Act: -0.0001

Data Index: 181761 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2280. Min Act: -0.0001

Data Index: 330996 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1481116 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1877. Min Act: -0.0001

Data Index: 765131 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1288312 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1851. Min Act: -0.0001

Data Index: 836588 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1919. Min Act: -0.0001

Data Index: 1431574 (Python Code)

Max Activating Token Index: 787

Text #8

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1751. Min Act: -0.0001

Data Index: 16421 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1811. Min Act: -0.0001

Data Index: 283438 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1795. Min Act: -0.0001

Data Index: 1092816 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1894. Min Act: -0.0001

Data Index: 745561 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1718. Min Act: -0.0001

Data Index: 498410 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1408242 (Python Code)

Max Activating Token Index: 132

Text #14

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1702. Min Act: -0.0001

Data Index: 834621 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1696. Min Act: -0.0001

Data Index: 974130 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1685. Min Act: -0.0001

Data Index: 1493711 (Python Code)

Max Activating Token Index: 337

Text #17

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1740. Min Act: -0.0001

Data Index: 1281202 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1299374 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.2754. Min Range: -0.2754

Max Act: 0.1682. Min Act: -0.0001

Data Index: 877873 (C4 (Web Text))

Max Activating Token Index: 975