< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 28 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4924. Min Act: -0.0002

Data Index: 1792402 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4890. Min Act: -0.0001

Data Index: 1857324 (The Pile)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1446855 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4493. Min Act: -0.0002

Data Index: 1623975 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4194. Min Act: -0.0001

Data Index: 250534 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4253. Min Act: -0.0002

Data Index: 631316 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4404. Min Act: -0.0001

Data Index: 523840 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4097. Min Act: -0.0001

Data Index: 1151146 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4201. Min Act: -0.0001

Data Index: 1579665 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4451. Min Act: -0.0002

Data Index: 1694371 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4289. Min Act: -0.0002

Data Index: 319816 (The Pile)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4709. Min Act: -0.0002

Data Index: 84768 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4511. Min Act: -0.0002

Data Index: 501293 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4243. Min Act: -0.0002

Data Index: 926314 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4165. Min Act: -0.0001

Data Index: 886128 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3819. Min Act: -0.0001

Data Index: 530148 (The Pile)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.4053. Min Act: -0.0002

Data Index: 829243 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3886. Min Act: -0.0002

Data Index: 755681 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3855. Min Act: -0.0002

Data Index: 1671993 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4924. Min Range: -0.4924

Max Act: 0.3956. Min Act: -0.0001

Data Index: 1605119 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #19