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

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

Neuron 346 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5827. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5867. Min Act: -0.0000

Data Index: 193305 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5603. Min Act: -0.0000

Data Index: 866198 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5003. Min Act: -0.0000

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5212. Min Act: -0.0000

Data Index: 238113 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5215. Min Act: -0.0000

Data Index: 529823 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4919. Min Act: -0.0000

Data Index: 745602 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.5084. Min Act: -0.0000

Data Index: 2670 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4886. Min Act: -0.0000

Data Index: 99580 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4896. Min Act: -0.0000

Data Index: 999856 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1108347 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1182428 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4836. Min Act: -0.0000

Data Index: 706196 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4876. Min Act: -0.0000

Data Index: 511733 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4586. Min Act: -0.0000

Data Index: 450051 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4561. Min Act: -0.0000

Data Index: 422386 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4504. Min Act: 0.0000

Data Index: 1313201 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4684. Min Act: -0.0000

Data Index: 23413 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4417. Min Act: -0.0000

Data Index: 220292 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.5867. Min Range: -0.5867

Max Act: 0.4404. Min Act: -0.0000

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 679