< Prev | Home | Model | Random | Next >

Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5097 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')



Text #0

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.9661. Min Act: -0.0000

Data Index: 1702488 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8556. Min Act: -0.0000

Data Index: 1115216 (The Pile)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.9523. Min Act: -0.0000

Data Index: 1770159 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0327. Min Range: -2.0327

Max Act: 2.0327. Min Act: -0.0000

Data Index: 202251 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8181. Min Act: -0.0000

Data Index: 1707167 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8283. Min Act: -0.0000

Data Index: 1259861 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1011710 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8873. Min Act: -0.0000

Data Index: 1121841 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8626. Min Act: -0.0000

Data Index: 1795775 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.5414. Min Act: -0.0000

Data Index: 1403048 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.7264. Min Act: -0.0000

Data Index: 723671 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8206. Min Act: -0.0000

Data Index: 1133865 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8113. Min Act: -0.0000

Data Index: 569978 (The Pile)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.7723. Min Act: -0.0000

Data Index: 757678 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.6536. Min Act: -0.0000

Data Index: 868690 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1270604 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.7323. Min Act: -0.0000

Data Index: 1108925 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.6319. Min Act: -0.0000

Data Index: 219779 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.8286. Min Act: -0.0000

Data Index: 1107998 (The Pile)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0327. Min Range: -2.0327

Max Act: 1.7087. Min Act: -0.0000

Data Index: 1935160 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #19