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

Dataset: The Pile

Neuron 229 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: 1.7435. Min Range: -1.7435

Max Act: 1.6265. Min Act: -0.0000

Data Index: 935546 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6727. Min Act: -0.0000

Data Index: 699013 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.4557. Min Act: -0.0000

Data Index: 1078356 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6782. Min Act: -0.0000

Data Index: 615592 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6376. Min Act: -0.0000

Data Index: 943151 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1937894 (The Pile)

Max Activating Token Index: 7

Text #6

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6795. Min Act: -0.0000

Data Index: 525567 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.4915. Min Act: -0.0000

Data Index: 211883 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1805069 (The Pile)

Max Activating Token Index: 988

Text #9

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6199. Min Act: -0.0000

Data Index: 1343081 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.5676. Min Act: -0.0000

Data Index: 605681 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.5958. Min Act: -0.0000

Data Index: 176221 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6829. Min Act: -0.0000

Data Index: 811100 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.5431. Min Act: -0.0000

Data Index: 1501495 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.5739. Min Act: -0.0000

Data Index: 609662 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1998730 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.5261. Min Act: -0.0000

Data Index: 1913067 (The Pile)

Max Activating Token Index: 205

Text #17

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.6115. Min Act: -0.0000

Data Index: 396691 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1887685 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 1.7435. Min Range: -1.7435

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1043683 (The Pile)

Max Activating Token Index: 964