< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.6057. Min Act: -0.0001

Data Index: 1999128 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5896. Min Act: -0.0001

Data Index: 1251717 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5452. Min Act: -0.0001

Data Index: 1510277 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5422. Min Act: -0.0001

Data Index: 279301 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5305. Min Act: -0.0001

Data Index: 1542481 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5192. Min Act: -0.0001

Data Index: 1456609 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5449. Min Act: -0.0001

Data Index: 220519 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3429. Min Act: -0.0001

Data Index: 531356 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4681. Min Act: -0.0001

Data Index: 637353 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3633. Min Act: -0.0001

Data Index: 1722547 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.5274. Min Act: -0.0001

Data Index: 1276802 (The Pile)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4231. Min Act: -0.0001

Data Index: 39090 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4055. Min Act: -0.0001

Data Index: 192448 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4806. Min Act: -0.0001

Data Index: 1548109 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3715. Min Act: -0.0001

Data Index: 873261 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2580. Min Act: -0.0001

Data Index: 1489799 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3257. Min Act: -0.0001

Data Index: 529691 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2230. Min Act: -0.0001

Data Index: 313375 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3651. Min Act: -0.0001

Data Index: 888835 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1059791 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #19