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

Dataset: The Pile

Neuron 109 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: 1.4342. Min Range: -1.4342

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1808533 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1866. Min Act: -0.0000

Data Index: 469785 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0464. Min Act: -0.0000

Data Index: 653333 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1540. Min Act: -0.0000

Data Index: 590711 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0921. Min Act: -0.0000

Data Index: 787873 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1333587 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.1070. Min Act: -0.0000

Data Index: 15810 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1015295 (The Pile)

Max Activating Token Index: 94

Text #8

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0430. Min Act: -0.0000

Data Index: 564932 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1891243 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1175847 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0328. Min Act: -0.0000

Data Index: 928275 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1590749 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.4342. Min Range: -1.4342

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1738214 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0093. Min Act: -0.0000

Data Index: 497298 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 1.4342. Min Range: -1.4342

Max Act: 0.9403. Min Act: -0.0000

Data Index: 539832 (The Pile)

Max Activating Token Index: 867

Text #16

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1699984 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 1.4342. Min Range: -1.4342

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1345972 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 1.4342. Min Range: -1.4342

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1023932 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 1.4342. Min Range: -1.4342

Max Act: 0.9815. Min Act: -0.0000

Data Index: 1053853 (The Pile)

Max Activating Token Index: 805