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

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

Neuron 408 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.8418. Min Act: -0.0000

Data Index: 938415 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.5652. Min Act: -0.0000

Data Index: 789292 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.3283. Min Act: -0.0000

Data Index: 465086 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.3114. Min Act: -0.0000

Data Index: 1055081 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.2877. Min Act: -0.0000

Data Index: 754291 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.4564. Min Act: -0.0000

Data Index: 637680 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.5513. Min Act: -0.0000

Data Index: 353786 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.6301. Min Act: -0.0000

Data Index: 1293980 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.2354. Min Act: -0.0000

Data Index: 1066129 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.4219. Min Act: -0.0000

Data Index: 1122450 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.1702. Min Act: -0.0000

Data Index: 907777 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.1265. Min Act: -0.0000

Data Index: 1272401 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.1653. Min Act: -0.0000

Data Index: 1530106 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.4380. Min Act: -0.0000

Data Index: 549688 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.2017. Min Act: -0.0000

Data Index: 681775 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.3201. Min Act: -0.0000

Data Index: 814360 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.0740. Min Act: -0.0000

Data Index: 547824 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.1793. Min Act: -0.0000

Data Index: 667659 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.0589. Min Act: -0.0000

Data Index: 698914 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 2.8418. Min Range: -2.8418

Max Act: 2.1733. Min Act: -0.0000

Data Index: 301854 (C4 (Web Text))

Max Activating Token Index: 665