Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5950 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1810. Min Range: -1.1810

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1620049 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1642204 (Python Code)

Max Activating Token Index: 872

Text #2

Max Range: 1.1810. Min Range: -1.1810

Max Act: 1.0464. Min Act: -0.0000

Data Index: 303663 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1591448 (Python Code)

Max Activating Token Index: 923

Text #4

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.9045. Min Act: -0.0000

Data Index: 370156 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1489290 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.8561. Min Act: -0.0000

Data Index: 275719 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.8321. Min Act: -0.0000

Data Index: 941717 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1000351 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1232195 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.7396. Min Act: -0.0000

Data Index: 118360 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1518657 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1348282 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.7262. Min Act: -0.0000

Data Index: 571364 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1526549 (Python Code)

Max Activating Token Index: 751

Text #15

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.7404. Min Act: -0.0000

Data Index: 1101768 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1570629 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.6732. Min Act: -0.0000

Data Index: 843868 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.6889. Min Act: -0.0000

Data Index: 620917 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 1.1810. Min Range: -1.1810

Max Act: 0.6981. Min Act: -0.0000

Data Index: 824496 (C4 (Web Text))

Max Activating Token Index: 500