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

Dataset: The Pile

Neuron 3972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1049244 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.9121. Min Act: -0.0000

Data Index: 5306 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1910308 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.7880. Min Act: -0.0000

Data Index: 332987 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.8760. Min Act: -0.0000

Data Index: 181899 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1989894 (The Pile)

Max Activating Token Index: 628

Text #6

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.7585. Min Act: -0.0000

Data Index: 521129 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.7903. Min Act: -0.0000

Data Index: 237364 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6884. Min Act: 0.0000

Data Index: 27333 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6675. Min Act: -0.0000

Data Index: 701503 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6688. Min Act: -0.0000

Data Index: 570960 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.7203. Min Act: 0.0000

Data Index: 327375 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1961841 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1801510 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1160818 (The Pile)

Max Activating Token Index: 570

Text #15

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1009088 (The Pile)

Max Activating Token Index: 360

Text #16

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6582. Min Act: -0.0000

Data Index: 725390 (The Pile)

Max Activating Token Index: 376

Text #17

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6108. Min Act: -0.0000

Data Index: 290322 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6431. Min Act: 0.0000

Data Index: 1196274 (The Pile)

Max Activating Token Index: 32

Text #19

Max Range: 0.9608. Min Range: -0.9608

Max Act: 0.6758. Min Act: -0.0000

Data Index: 333106 (The Pile)

Max Activating Token Index: 104