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

Dataset: The Pile

Neuron 1288 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.4715. Min Act: -0.0000

Data Index: 888521 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.8717. Min Act: -0.0000

Data Index: 1467305 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 5.4715. Min Range: -5.4715

Max Act: 5.1816. Min Act: -0.0000

Data Index: 1614747 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.3344. Min Act: -0.0000

Data Index: 1107674 (The Pile)

Max Activating Token Index: 850

Text #4

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.3101. Min Act: -0.0000

Data Index: 1136480 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.0916. Min Act: -0.0000

Data Index: 1555085 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.2270. Min Act: -0.0000

Data Index: 1550109 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.2400. Min Act: -0.0000

Data Index: 1423482 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.0795. Min Act: -0.0000

Data Index: 1315046 (The Pile)

Max Activating Token Index: 627

Text #9

Max Range: 5.4715. Min Range: -5.4715

Max Act: 4.0217. Min Act: -0.0000

Data Index: 6823 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.8029. Min Act: -0.0000

Data Index: 249290 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.7983. Min Act: 0.0001

Data Index: 21034 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.7780. Min Act: -0.0000

Data Index: 1981106 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.7707. Min Act: 0.0000

Data Index: 1250741 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.7676. Min Act: -0.0000

Data Index: 839500 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.5667. Min Act: -0.0000

Data Index: 1235911 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.7464. Min Act: -0.0000

Data Index: 855440 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.7199. Min Act: -0.0000

Data Index: 1067334 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.5486. Min Act: -0.0000

Data Index: 1561080 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 5.4715. Min Range: -5.4715

Max Act: 3.4043. Min Act: -0.0000

Data Index: 1887237 (The Pile)

Max Activating Token Index: 1018