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

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

Neuron 5871 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0605. Min Act: -0.0001

Data Index: 1350806 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0862. Min Act: -0.0001

Data Index: 331452 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9975. Min Act: -0.0000

Data Index: 160604 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9625. Min Act: -0.0001

Data Index: 971919 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1293110 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0184. Min Act: -0.0001

Data Index: 58888 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9758. Min Act: -0.0001

Data Index: 856176 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8541. Min Act: -0.0001

Data Index: 1067652 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9123. Min Act: -0.0001

Data Index: 1174273 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1148626 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8409. Min Act: -0.0001

Data Index: 1073713 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8687. Min Act: -0.0001

Data Index: 103328 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9820. Min Act: -0.0001

Data Index: 360544 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8889. Min Act: -0.0001

Data Index: 484473 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1028881 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7745. Min Act: -0.0000

Data Index: 281161 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7816. Min Act: -0.0001

Data Index: 1288870 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.7793. Min Act: -0.0000

Data Index: 20649 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8069. Min Act: -0.0001

Data Index: 785598 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8031. Min Act: -0.0000

Data Index: 64590 (C4 (Web Text))

Max Activating Token Index: 439