Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4553 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3626. Min Act: -0.0000

Data Index: 229183 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3420. Min Act: -0.0000

Data Index: 1401583 (Python Code)

Max Activating Token Index: 940

Text #2

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2689. Min Act: -0.0000

Data Index: 557062 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1480337 (Python Code)

Max Activating Token Index: 544

Text #4

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1621999 (Python Code)

Max Activating Token Index: 804

Text #5

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1562194 (Python Code)

Max Activating Token Index: 723

Text #6

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2625. Min Act: -0.0000

Data Index: 1243339 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1447617 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1474971 (Python Code)

Max Activating Token Index: 949

Text #9

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.3096. Min Act: -0.0000

Data Index: 608600 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1443204 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1501. Min Act: -0.0000

Data Index: 656348 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1477550 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1627. Min Act: -0.0000

Data Index: 281423 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1545023 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1367791 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0573. Min Act: -0.0000

Data Index: 1382733 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1563730 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.1127. Min Act: -0.0000

Data Index: 1448524 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 1.3626. Min Range: -1.3626

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1574911 (Python Code)

Max Activating Token Index: 890