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

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

Neuron 5413 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4715. Min Range: -2.4715

Max Act: 2.3572. Min Act: -0.0000

Data Index: 1392511 (Python Code)

Max Activating Token Index: 344

Text #1

Max Range: 2.4715. Min Range: -2.4715

Max Act: 2.4715. Min Act: -0.0000

Data Index: 1384678 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 2.4715. Min Range: -2.4715

Max Act: 2.0868. Min Act: -0.0000

Data Index: 1608611 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.9794. Min Act: -0.0000

Data Index: 1479219 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 2.4715. Min Range: -2.4715

Max Act: 2.0734. Min Act: -0.0000

Data Index: 577493 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 2.4715. Min Range: -2.4715

Max Act: 2.0113. Min Act: -0.0000

Data Index: 490919 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.7646. Min Act: -0.0000

Data Index: 189386 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.7074. Min Act: -0.0000

Data Index: 753177 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.6437. Min Act: -0.0000

Data Index: 131551 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.6194. Min Act: -0.0000

Data Index: 984693 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.6867. Min Act: -0.0000

Data Index: 1632156 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.5823. Min Act: -0.0000

Data Index: 342692 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.5660. Min Act: -0.0000

Data Index: 755905 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1084727 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1531681 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.6018. Min Act: -0.0000

Data Index: 1073220 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1094272 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.3757. Min Act: -0.0000

Data Index: 1475241 (Python Code)

Max Activating Token Index: 538

Text #18

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.4533. Min Act: -0.0000

Data Index: 67339 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 2.4715. Min Range: -2.4715

Max Act: 1.3602. Min Act: -0.0000

Data Index: 921832 (C4 (Web Text))

Max Activating Token Index: 810