< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 1935 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: 0.6000. Min Range: -0.6000

Max Act: 0.6000. Min Act: -0.0002

Data Index: 847521 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5321. Min Act: -0.0002

Data Index: 115489 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5240. Min Act: -0.0002

Data Index: 1609246 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5241. Min Act: -0.0002

Data Index: 1700437 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5351. Min Act: -0.0002

Data Index: 1517036 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5283. Min Act: -0.0002

Data Index: 477461 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5107. Min Act: -0.0002

Data Index: 1855316 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4865. Min Act: -0.0002

Data Index: 945524 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5178. Min Act: -0.0002

Data Index: 1266912 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4937. Min Act: -0.0002

Data Index: 1197195 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4926. Min Act: -0.0002

Data Index: 1239973 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4894. Min Act: -0.0002

Data Index: 777959 (The Pile)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4758. Min Act: -0.0002

Data Index: 1928546 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5075. Min Act: -0.0002

Data Index: 1652363 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4910. Min Act: -0.0002

Data Index: 124147 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5053. Min Act: -0.0002

Data Index: 1378001 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4874. Min Act: -0.0002

Data Index: 1629792 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4690. Min Act: -0.0002

Data Index: 751741 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4848. Min Act: -0.0002

Data Index: 1562653 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4796. Min Act: -0.0002

Data Index: 91038 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #19