< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3037 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: 0.2920. Min Range: -0.2920

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1579633 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2690. Min Act: -0.0000

Data Index: 167373 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2756. Min Act: 0.0000

Data Index: 202336 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1853220 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1409671 (The Pile)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1362795 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2392. Min Act: -0.0000

Data Index: 466651 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2235. Min Act: 0.0000

Data Index: 1254852 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1320772 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2392. Min Act: 0.0000

Data Index: 169417 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2381. Min Act: -0.0001

Data Index: 863721 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2255. Min Act: -0.0000

Data Index: 922115 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2244. Min Act: -0.0000

Data Index: 702088 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2225. Min Act: -0.0000

Data Index: 355156 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2196. Min Act: -0.0000

Data Index: 521356 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2073. Min Act: -0.0000

Data Index: 151239 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1461027 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2199. Min Act: -0.0000

Data Index: 956799 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1005255 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2920. Min Range: -0.2920

Max Act: 0.2057. Min Act: 0.0000

Data Index: 1568740 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #19