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

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

Neuron 4740 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: 0.9794. Min Range: -0.9794

Max Act: 0.9794. Min Act: -0.0000

Data Index: 645496 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5833. Min Act: -0.0000

Data Index: 357930 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1155357 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1357550 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1245474 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5383. Min Act: -0.0000

Data Index: 446126 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5465. Min Act: -0.0000

Data Index: 996485 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1231883 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1348470 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.5080. Min Act: -0.0000

Data Index: 679745 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4690. Min Act: -0.0000

Data Index: 600252 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4590. Min Act: -0.0000

Data Index: 493093 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4617. Min Act: -0.0000

Data Index: 334220 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4583. Min Act: -0.0000

Data Index: 225861 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4460. Min Act: -0.0000

Data Index: 394863 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4332. Min Act: -0.0000

Data Index: 524586 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1099863 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4342. Min Act: -0.0000

Data Index: 994988 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1057214 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.9794. Min Range: -0.9794

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1005096 (C4 (Web Text))

Max Activating Token Index: 957