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

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

Neuron 5120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.6311. Min Act: -0.0000

Data Index: 726170 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1310055 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5271. Min Act: -0.0000

Data Index: 577026 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5248. Min Act: -0.0000

Data Index: 358484 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5183. Min Act: -0.0000

Data Index: 18680 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1163142 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.5018. Min Act: -0.0000

Data Index: 607308 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4941. Min Act: -0.0000

Data Index: 43696 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4777. Min Act: -0.0000

Data Index: 576976 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1088360 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4814. Min Act: -0.0000

Data Index: 751683 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1137019 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4438. Min Act: -0.0000

Data Index: 756062 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1328072 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4344. Min Act: -0.0000

Data Index: 931253 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1240977 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4126. Min Act: -0.0000

Data Index: 403287 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4201. Min Act: -0.0000

Data Index: 966788 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4188. Min Act: -0.0000

Data Index: 276771 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.6311. Min Range: -0.6311

Max Act: 0.4338. Min Act: -0.0000

Data Index: 548720 (C4 (Web Text))

Max Activating Token Index: 610