< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 6 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.2275. Min Act: -0.0001

Data Index: 427392 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1721. Min Act: -0.0001

Data Index: 703120 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1027. Min Act: -0.0001

Data Index: 836718 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0832. Min Act: -0.0001

Data Index: 1858226 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1355. Min Act: -0.0001

Data Index: 1714548 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0812. Min Act: -0.0001

Data Index: 43425 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.1487. Min Act: -0.0001

Data Index: 321376 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0557. Min Act: -0.0001

Data Index: 1121476 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0475. Min Act: -0.0001

Data Index: 233532 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0451. Min Act: -0.0001

Data Index: 808304 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0399. Min Act: -0.0001

Data Index: 1178474 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1940936 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0314. Min Act: -0.0001

Data Index: 1993783 (The Pile)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0842. Min Act: -0.0001

Data Index: 1849824 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0229. Min Act: -0.0001

Data Index: 1731459 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1948332 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2275. Min Range: -1.2275

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1575309 (The Pile)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1477183 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9988. Min Act: -0.0001

Data Index: 1059935 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2275. Min Range: -1.2275

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1809830 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #19