Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1641 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4875. Min Range: -2.4875

Max Act: 2.4875. Min Act: -0.0000

Data Index: 825152 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 2.4875. Min Range: -2.4875

Max Act: 2.2852. Min Act: -0.0000

Data Index: 335842 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 2.4875. Min Range: -2.4875

Max Act: 2.0991. Min Act: -0.0000

Data Index: 639399 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 2.4875. Min Range: -2.4875

Max Act: 2.2581. Min Act: -0.0000

Data Index: 885485 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1060063 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.8825. Min Act: -0.0000

Data Index: 404698 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.4836. Min Act: -0.0000

Data Index: 879171 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1272058 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.6756. Min Act: -0.0000

Data Index: 673193 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.7688. Min Act: -0.0000

Data Index: 571420 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.5567. Min Act: -0.0000

Data Index: 194310 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.5351. Min Act: -0.0000

Data Index: 475472 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.4105. Min Act: -0.0000

Data Index: 464795 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.5436. Min Act: -0.0000

Data Index: 177217 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.4642. Min Act: -0.0000

Data Index: 99493 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.4221. Min Act: -0.0000

Data Index: 902354 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.4162. Min Act: -0.0000

Data Index: 119177 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1067186 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.3272. Min Act: -0.0000

Data Index: 534606 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 2.4875. Min Range: -2.4875

Max Act: 1.3080. Min Act: -0.0000

Data Index: 613637 (C4 (Web Text))

Max Activating Token Index: 149