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

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

Neuron 4028 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: 1.6936. Min Range: -1.6936

Max Act: 1.6936. Min Act: -0.0000

Data Index: 920600 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.3822. Min Act: -0.0000

Data Index: 918572 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.2909. Min Act: -0.0000

Data Index: 406250 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.2506. Min Act: -0.0000

Data Index: 35793 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.3217. Min Act: -0.0000

Data Index: 583692 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.2328. Min Act: -0.0000

Data Index: 287496 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.2664. Min Act: -0.0000

Data Index: 68815 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.6936. Min Range: -1.6936

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1327143 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0945. Min Act: -0.0000

Data Index: 284824 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1130117 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0530. Min Act: -0.0000

Data Index: 584326 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1319122 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0437. Min Act: -0.0000

Data Index: 334483 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0325. Min Act: -0.0000

Data Index: 449779 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0928. Min Act: -0.0000

Data Index: 115947 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1221356 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1144750 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.6936. Min Range: -1.6936

Max Act: 1.0540. Min Act: -0.0000

Data Index: 583765 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.6936. Min Range: -1.6936

Max Act: 0.9688. Min Act: -0.0000

Data Index: 927469 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.6936. Min Range: -1.6936

Max Act: 0.9663. Min Act: -0.0000

Data Index: 321694 (C4 (Web Text))

Max Activating Token Index: 55