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

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

Neuron 3489 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1264585 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0717. Min Act: -0.0000

Data Index: 379515 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1018392 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0721. Min Act: -0.0000

Data Index: 558893 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0651. Min Act: -0.0000

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1286159 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0651. Min Act: -0.0000

Data Index: 905904 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0626. Min Act: -0.0000

Data Index: 64601 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1152566 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0634. Min Act: -0.0000

Data Index: 865543 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0602. Min Act: -0.0000

Data Index: 114377 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0642. Min Act: -0.0000

Data Index: 301754 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1608896 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0521. Min Act: -0.0000

Data Index: 84078 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0550. Min Act: -0.0000

Data Index: 329015 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0532. Min Act: -0.0000

Data Index: 363860 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0568. Min Act: -0.0000

Data Index: 982745 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0585. Min Act: -0.0000

Data Index: 469607 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0527. Min Act: -0.0000

Data Index: 231517 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.1004. Min Range: -0.1004

Max Act: 0.0542. Min Act: -0.0000

Data Index: 390050 (C4 (Web Text))

Max Activating Token Index: 170