< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 32 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.9387. Min Act: -0.0000

Data Index: 671708 (The Pile)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7449. Min Act: 0.0000

Data Index: 1200813 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.5105. Min Act: -0.0000

Data Index: 898143 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.4957. Min Act: -0.0000

Data Index: 1565634 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3772. Min Act: 0.0000

Data Index: 1579114 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1898959 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3328. Min Act: -0.0000

Data Index: 100563 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1125719 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3243. Min Act: -0.0000

Data Index: 431750 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3888. Min Act: -0.0000

Data Index: 840126 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.2854. Min Act: -0.0000

Data Index: 1524988 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1079155 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3325. Min Act: -0.0000

Data Index: 582884 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1783716 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1398804 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.3125. Min Act: -0.0000

Data Index: 423691 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1138828 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.2768. Min Act: -0.0000

Data Index: 869358 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1186239 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.2665. Min Act: -0.0000

Data Index: 671064 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #19