< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 36 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 2.2292. Min Range: -2.2292

Max Act: 2.2292. Min Act: -0.0000

Data Index: 1585569 (The Pile)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2292. Min Range: -2.2292

Max Act: 2.0385. Min Act: -0.0000

Data Index: 1264995 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.7877. Min Act: -0.0000

Data Index: 1424178 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.8776. Min Act: -0.0000

Data Index: 1196804 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.7614. Min Act: -0.0000

Data Index: 80823 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6790. Min Act: -0.0000

Data Index: 186090 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.7284. Min Act: -0.0000

Data Index: 1930001 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1233130 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1578834 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6909. Min Act: -0.0000

Data Index: 291314 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.5987. Min Act: -0.0000

Data Index: 1293234 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6286. Min Act: -0.0000

Data Index: 24831 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1945907 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.5727. Min Act: -0.0000

Data Index: 49406 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.5725. Min Act: -0.0000

Data Index: 656536 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.5752. Min Act: -0.0000

Data Index: 86036 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6437. Min Act: -0.0000

Data Index: 1739015 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6175. Min Act: -0.0000

Data Index: 1656811 (The Pile)

Max Activating Token Index: 1020

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1438185 (The Pile)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2292. Min Range: -2.2292

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1960708 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #19