< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 212 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.7708. Min Act: -0.0000

Data Index: 270228 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.4436. Min Act: -0.0000

Data Index: 1197697 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.0755. Min Act: -0.0000

Data Index: 1213794 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7708. Min Range: -2.7708

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1943470 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.7927. Min Act: -0.0000

Data Index: 1964675 (The Pile)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1035237 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.7926. Min Act: -0.0000

Data Index: 1962411 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.7771. Min Act: -0.0000

Data Index: 581864 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.5581. Min Act: -0.0000

Data Index: 1363034 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.5533. Min Act: -0.0000

Data Index: 1878181 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.6230. Min Act: -0.0000

Data Index: 246913 (The Pile)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.4218. Min Act: 0.0000

Data Index: 502098 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.5032. Min Act: -0.0000

Data Index: 1765379 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.3720. Min Act: -0.0000

Data Index: 620397 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.3661. Min Act: -0.0000

Data Index: 1171709 (The Pile)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1460402 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.5116. Min Act: -0.0000

Data Index: 85281 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.3512. Min Act: 0.0000

Data Index: 203934 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1318539 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7708. Min Range: -2.7708

Max Act: 1.5195. Min Act: -0.0000

Data Index: 1095301 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #19