< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 49 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.4876. Min Act: -0.0000

Data Index: 137786 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.5386. Min Act: -0.0000

Data Index: 124455 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1759909 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.5337. Min Act: -0.0000

Data Index: 1656975 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.3942. Min Act: -0.0000

Data Index: 409402 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.4029. Min Act: -0.0000

Data Index: 117278 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.3860. Min Act: -0.0000

Data Index: 720539 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.2611. Min Act: -0.0000

Data Index: 252414 (The Pile)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1892078 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.3369. Min Act: -0.0000

Data Index: 569944 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1232. Min Act: -0.0000

Data Index: 1079433 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1971502 (The Pile)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0165. Min Act: -0.0000

Data Index: 901407 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.2212. Min Act: -0.0000

Data Index: 373976 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1493623 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1082. Min Act: -0.0000

Data Index: 56705 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0373. Min Act: -0.0000

Data Index: 341592 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1529267 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0321. Min Act: -0.0000

Data Index: 530266 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0806. Min Act: -0.0000

Data Index: 806602 (The Pile)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #19