< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3056 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.8969. Min Act: -0.0001

Data Index: 1316165 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.7778. Min Act: -0.0001

Data Index: 297344 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1816310 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6308. Min Act: -0.0001

Data Index: 637844 (The Pile)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6059. Min Act: -0.0000

Data Index: 614422 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6885. Min Act: -0.0001

Data Index: 732023 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.7049. Min Act: -0.0001

Data Index: 980011 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6786. Min Act: -0.0001

Data Index: 1747218 (The Pile)

Max Activating Token Index: 357

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6457. Min Act: -0.0001

Data Index: 26959 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6883. Min Act: -0.0001

Data Index: 1177489 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.7540. Min Act: -0.0000

Data Index: 240472 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1468979 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1060588 (The Pile)

Max Activating Token Index: 230

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6550. Min Act: -0.0001

Data Index: 422254 (The Pile)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6163. Min Act: -0.0001

Data Index: 1712274 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1922058 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6307. Min Act: -0.0001

Data Index: 1048699 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.5637. Min Act: -0.0001

Data Index: 528488 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6269. Min Act: -0.0001

Data Index: 297522 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8969. Min Range: -0.8969

Max Act: 0.6248. Min Act: -0.0000

Data Index: 811000 (The Pile)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #19