< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5094 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.8469. Min Act: -0.0000

Data Index: 929932 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.8116. Min Act: -0.0000

Data Index: 635917 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7517. Min Act: -0.0000

Data Index: 986159 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1300334 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7285. Min Act: -0.0000

Data Index: 41281 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1927701 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7341. Min Act: -0.0000

Data Index: 91807 (The Pile)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6886. Min Act: -0.0000

Data Index: 18462 (The Pile)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7506. Min Act: -0.0000

Data Index: 1189177 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7040. Min Act: -0.0000

Data Index: 179824 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1606205 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7118. Min Act: -0.0000

Data Index: 23485 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7087. Min Act: -0.0000

Data Index: 591837 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1967761 (The Pile)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7006. Min Act: -0.0000

Data Index: 428743 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1535419 (The Pile)

Max Activating Token Index: 706

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1535278 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.7165. Min Act: -0.0000

Data Index: 209513 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6829. Min Act: -0.0000

Data Index: 857344 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.8469. Min Range: -0.8469

Max Act: 0.6972. Min Act: -0.0000

Data Index: 396011 (The Pile)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #19