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

Dataset: The Pile

Neuron 2345 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1488770 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.2793. Min Act: -0.0000

Data Index: 518968 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1566. Min Act: -0.0000

Data Index: 219768 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1741. Min Act: -0.0000

Data Index: 1146358 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0290. Min Act: -0.0000

Data Index: 148411 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1147. Min Act: -0.0000

Data Index: 328896 (The Pile)

Max Activating Token Index: 5

Text #6

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1132680 (The Pile)

Max Activating Token Index: 5

Text #7

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1455. Min Act: -0.0000

Data Index: 751093 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1455. Min Act: -0.0000

Data Index: 1014917 (The Pile)

Max Activating Token Index: 5

Text #9

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0987. Min Act: -0.0000

Data Index: 550630 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0857. Min Act: -0.0000

Data Index: 366227 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0648. Min Act: -0.0000

Data Index: 466533 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1210996 (The Pile)

Max Activating Token Index: 280

Text #13

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0611. Min Act: -0.0000

Data Index: 893442 (The Pile)

Max Activating Token Index: 5

Text #14

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0611. Min Act: -0.0000

Data Index: 477232 (The Pile)

Max Activating Token Index: 5

Text #15

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0611. Min Act: -0.0000

Data Index: 845688 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1557088 (The Pile)

Max Activating Token Index: 5

Text #17

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1157279 (The Pile)

Max Activating Token Index: 5

Text #18

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0611. Min Act: -0.0000

Data Index: 466665 (The Pile)

Max Activating Token Index: 5

Text #19

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0653. Min Act: -0.0000

Data Index: 1552463 (The Pile)

Max Activating Token Index: 426