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

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

Neuron 5624 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: 0.0890. Min Range: -0.0890

Max Act: 0.0890. Min Act: -0.0000

Data Index: 762949 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0774. Min Act: -0.0000

Data Index: 896442 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0829. Min Act: -0.0001

Data Index: 150631 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0775. Min Act: -0.0001

Data Index: 501159 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0780. Min Act: -0.0001

Data Index: 955291 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0663. Min Act: -0.0001

Data Index: 853475 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0651. Min Act: -0.0000

Data Index: 1580437 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0454. Min Act: -0.0001

Data Index: 904524 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1266377 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0703. Min Act: -0.0001

Data Index: 758686 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0754. Min Act: -0.0000

Data Index: 448887 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1462219 (Python Code)

Max Activating Token Index: 981

Text #12

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1528992 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1391343 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0566. Min Act: -0.0001

Data Index: 192180 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1115804 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1459438 (Python Code)

Max Activating Token Index: 963

Text #17

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0530. Min Act: -0.0001

Data Index: 945523 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1522813 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 0.0890. Min Range: -0.0890

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1594706 (Python Code)

Max Activating Token Index: 850