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

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

Neuron 4540 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0549. Min Range: -4.0549

Max Act: 4.0549. Min Act: -0.0001

Data Index: 609340 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.7254. Min Act: -0.0000

Data Index: 986619 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.6984. Min Act: -0.0000

Data Index: 766202 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.6599. Min Act: -0.0001

Data Index: 246160 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.6739. Min Act: -0.0001

Data Index: 141617 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.5940. Min Act: -0.0000

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.5624. Min Act: -0.0000

Data Index: 334519 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.2217. Min Act: -0.0000

Data Index: 76946 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.4801. Min Act: -0.0000

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.4538. Min Act: -0.0001

Data Index: 8903 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.4481. Min Act: -0.0001

Data Index: 254585 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.2287. Min Act: -0.0000

Data Index: 939834 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.1689. Min Act: -0.0000

Data Index: 472934 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.4356. Min Act: -0.0000

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.2787. Min Act: -0.0001

Data Index: 715847 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.4181. Min Act: -0.0000

Data Index: 1206414 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.0549. Min Act: -0.0000

Data Index: 533744 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.2069. Min Act: -0.0000

Data Index: 667156 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.1858. Min Act: -0.0001

Data Index: 1298257 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 4.0549. Min Range: -4.0549

Max Act: 3.0286. Min Act: -0.0000

Data Index: 558706 (C4 (Web Text))

Max Activating Token Index: 257