< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 24 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1889613 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.2395. Min Range: -1.2395

Max Act: 1.0855. Min Act: 0.0000

Data Index: 1498301 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9427. Min Act: -0.0000

Data Index: 670994 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1186400 (The Pile)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9760. Min Act: 0.0000

Data Index: 1241383 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1185680 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9467. Min Act: 0.0000

Data Index: 1592352 (The Pile)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1549275 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1697249 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1356764 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1111263 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8504. Min Act: -0.0000

Data Index: 577501 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8361. Min Act: 0.0000

Data Index: 1785460 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8047. Min Act: 0.0000

Data Index: 1283664 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8333. Min Act: -0.0000

Data Index: 803389 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.7883. Min Act: 0.0000

Data Index: 1418057 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1734970 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1814986 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8331. Min Act: -0.0000

Data Index: 282602 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.2395. Min Range: -1.2395

Max Act: 0.8424. Min Act: 0.0000

Data Index: 505190 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #19