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

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

Neuron 114 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.7390. Min Act: -0.0000

Data Index: 329601 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.6773. Min Act: -0.0000

Data Index: 1301276 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.5688. Min Act: -0.0000

Data Index: 817662 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.7511. Min Act: -0.0000

Data Index: 784705 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1003502 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.4622. Min Act: -0.0000

Data Index: 493568 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.4845. Min Act: -0.0000

Data Index: 356734 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1221318 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.5390. Min Act: -0.0000

Data Index: 846241 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1040032 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.3258. Min Act: -0.0000

Data Index: 634092 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1071891 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.2898. Min Act: -0.0000

Data Index: 543789 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.2814. Min Act: -0.0000

Data Index: 1203105 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.3347. Min Act: -0.0000

Data Index: 669779 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.2764. Min Act: -0.0000

Data Index: 959929 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1044065 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.3262. Min Act: -0.0000

Data Index: 957829 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.1875. Min Act: -0.0000

Data Index: 61175 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 1.7511. Min Range: -1.7511

Max Act: 1.2585. Min Act: -0.0000

Data Index: 828479 (C4 (Web Text))

Max Activating Token Index: 589