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

Dataset: The Pile

Neuron 3073 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1992. Min Range: -1.1992

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1250645 (The Pile)

Max Activating Token Index: 15

Text #1

Max Range: 1.1992. Min Range: -1.1992

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1453391 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 1.1992. Min Range: -1.1992

Max Act: 1.0657. Min Act: -0.0000

Data Index: 33210 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 1.1992. Min Range: -1.1992

Max Act: 1.0487. Min Act: -0.0000

Data Index: 208198 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 1.1992. Min Range: -1.1992

Max Act: 1.0137. Min Act: -0.0000

Data Index: 927985 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 1.1992. Min Range: -1.1992

Max Act: 1.0509. Min Act: -0.0000

Data Index: 29861 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.9305. Min Act: -0.0000

Data Index: 427208 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.9484. Min Act: -0.0000

Data Index: 767973 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.9387. Min Act: -0.0000

Data Index: 21204 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.9493. Min Act: -0.0000

Data Index: 805412 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1488467 (The Pile)

Max Activating Token Index: 84

Text #11

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1866602 (The Pile)

Max Activating Token Index: 394

Text #12

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8514. Min Act: -0.0000

Data Index: 137365 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.9059. Min Act: -0.0000

Data Index: 431067 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1154315 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8741. Min Act: -0.0000

Data Index: 273096 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8472. Min Act: -0.0000

Data Index: 785402 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.7610. Min Act: -0.0000

Data Index: 756788 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8326. Min Act: -0.0000

Data Index: 73790 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 1.1992. Min Range: -1.1992

Max Act: 0.8410. Min Act: -0.0000

Data Index: 699436 (The Pile)

Max Activating Token Index: 65