< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 36 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2869. Min Act: -0.0001

Data Index: 1175298 (The Pile)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2561. Min Act: -0.0001

Data Index: 577545 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2405. Min Act: -0.0001

Data Index: 7974 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2272. Min Act: -0.0001

Data Index: 680161 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2394. Min Act: -0.0001

Data Index: 972695 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2315. Min Act: -0.0001

Data Index: 849527 (The Pile)

Max Activating Token Index: 864

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1504912 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1333462 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2302. Min Act: -0.0001

Data Index: 151092 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2301. Min Act: -0.0001

Data Index: 896162 (The Pile)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2107. Min Act: -0.0001

Data Index: 689405 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2104. Min Act: -0.0001

Data Index: 941485 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2076. Min Act: -0.0001

Data Index: 823872 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2252. Min Act: -0.0001

Data Index: 837329 (The Pile)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2223. Min Act: -0.0001

Data Index: 288559 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1364384 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2301. Min Act: -0.0001

Data Index: 102463 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2130. Min Act: -0.0001

Data Index: 1214528 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1962300 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2869. Min Range: -0.2869

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1409105 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #19