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

Dataset: The Pile

Neuron 4965 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: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1442529 (The Pile)

Max Activating Token Index: 61

Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6152. Min Act: -0.0000

Data Index: 881567 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5682. Min Act: -0.0000

Data Index: 175166 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1070565 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1180351 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5198. Min Act: -0.0000

Data Index: 697926 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1515713 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4611. Min Act: -0.0000

Data Index: 681416 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4594. Min Act: -0.0000

Data Index: 36067 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1430867 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4111. Min Act: -0.0000

Data Index: 418873 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1717327 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1915553 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1005589 (The Pile)

Max Activating Token Index: 838

Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3845. Min Act: -0.0000

Data Index: 540216 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3807. Min Act: -0.0000

Data Index: 1382415 (The Pile)

Max Activating Token Index: 731

Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1545231 (The Pile)

Max Activating Token Index: 478

Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3563. Min Act: -0.0000

Data Index: 692336 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1616857 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1240774 (The Pile)

Max Activating Token Index: 133