< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.3104. Min Act: -0.0001

Data Index: 833110 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2504. Min Act: -0.0001

Data Index: 1498109 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2657. Min Act: -0.0001

Data Index: 405775 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2535. Min Act: -0.0001

Data Index: 432862 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2454. Min Act: -0.0001

Data Index: 430515 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1729954 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1804903 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2438. Min Act: -0.0001

Data Index: 292220 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2406. Min Act: -0.0001

Data Index: 809717 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2382. Min Act: -0.0001

Data Index: 772031 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2436. Min Act: -0.0001

Data Index: 1201513 (The Pile)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2350. Min Act: -0.0001

Data Index: 1798462 (The Pile)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2228. Min Act: -0.0001

Data Index: 821730 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2268. Min Act: -0.0001

Data Index: 215456 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2194. Min Act: -0.0001

Data Index: 1528630 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1547478 (The Pile)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1588703 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2048. Min Act: -0.0001

Data Index: 1451848 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1395015 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3104. Min Range: -0.3104

Max Act: 0.2092. Min Act: -0.0001

Data Index: 264267 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #19