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

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

Neuron 49 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.9896. Min Act: 0.0002

Data Index: 955422 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1225256 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7968. Min Act: -0.0000

Data Index: 361386 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7446. Min Act: 0.0000

Data Index: 865355 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1072411 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7563. Min Act: -0.0000

Data Index: 223856 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.7211. Min Act: -0.0000

Data Index: 459446 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6454. Min Act: -0.0000

Data Index: 229742 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6591. Min Act: 0.0000

Data Index: 893619 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6582. Min Act: -0.0000

Data Index: 893720 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6584. Min Act: -0.0000

Data Index: 5292 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6516. Min Act: -0.0000

Data Index: 540307 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.5866. Min Act: -0.0000

Data Index: 861219 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6011. Min Act: -0.0000

Data Index: 406055 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1062175 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1284662 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6062. Min Act: -0.0000

Data Index: 899242 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6021. Min Act: -0.0000

Data Index: 247043 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.6600. Min Act: -0.0000

Data Index: 260646 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.9896. Min Range: -0.9896

Max Act: 0.5936. Min Act: -0.0000

Data Index: 17531 (C4 (Web Text))

Max Activating Token Index: 775