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

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

Neuron 1974 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: 1.6003. Min Range: -1.6003

Max Act: 1.5456. Min Act: -0.0000

Data Index: 1165741 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.5709. Min Act: -0.0000

Data Index: 586098 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.4761. Min Act: -0.0000

Data Index: 449139 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.6003. Min Act: -0.0000

Data Index: 928704 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.5427. Min Act: -0.0000

Data Index: 945473 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.4110. Min Act: -0.0000

Data Index: 75425 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.4084. Min Act: -0.0000

Data Index: 1208176 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.3150. Min Act: -0.0000

Data Index: 210707 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.4615. Min Act: -0.0000

Data Index: 331695 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2551. Min Act: -0.0000

Data Index: 261136 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1350874 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1325702 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2918. Min Act: -0.0000

Data Index: 829421 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2861. Min Act: -0.0000

Data Index: 537989 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2863. Min Act: -0.0000

Data Index: 342094 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2107. Min Act: -0.0000

Data Index: 874713 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2870. Min Act: -0.0000

Data Index: 660665 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2069. Min Act: -0.0000

Data Index: 830756 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.2801. Min Act: -0.0000

Data Index: 356584 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.6003. Min Range: -1.6003

Max Act: 1.1937. Min Act: -0.0000

Data Index: 632393 (C4 (Web Text))

Max Activating Token Index: 380