< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 6 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.1028. Min Act: -0.0000

Data Index: 82368 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.0407. Min Act: -0.0000

Data Index: 1208481 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.1391. Min Act: -0.0000

Data Index: 995653 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.1085. Min Act: -0.0000

Data Index: 41337 (The Pile)

Max Activating Token Index: 297

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9937. Min Act: -0.0000

Data Index: 1228328 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.0557. Min Act: -0.0000

Data Index: 931753 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.1611. Min Act: -0.0000

Data Index: 1006688 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.0265. Min Act: -0.0000

Data Index: 1915182 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.0272. Min Act: -0.0000

Data Index: 1358893 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.1176. Min Act: -0.0000

Data Index: 281519 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9858. Min Act: -0.0000

Data Index: 1743620 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9887. Min Act: -0.0000

Data Index: 89986 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.8726. Min Act: -0.0000

Data Index: 827191 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9808. Min Act: -0.0000

Data Index: 1104611 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9680. Min Act: -0.0000

Data Index: 1783942 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.0210. Min Act: -0.0000

Data Index: 450244 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9423. Min Act: -0.0000

Data Index: 1448600 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1611. Min Range: -2.1611

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1310968 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9395. Min Act: -0.0000

Data Index: 764136 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1611. Min Range: -2.1611

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1103468 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #19