< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 26 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1940. Min Act: -0.0001

Data Index: 419790 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1786826 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1747903 (The Pile)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1681. Min Act: -0.0001

Data Index: 617798 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1575. Min Act: -0.0001

Data Index: 658639 (The Pile)

Max Activating Token Index: 887

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1502. Min Act: -0.0001

Data Index: 834135 (The Pile)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1668817 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1597. Min Act: -0.0001

Data Index: 677606 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1529. Min Act: -0.0001

Data Index: 366723 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1082148 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1143838 (The Pile)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1288587 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1514. Min Act: -0.0001

Data Index: 1947610 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1354462 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1618033 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1491. Min Act: -0.0001

Data Index: 66278 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1596. Min Act: -0.0001

Data Index: 98698 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1377. Min Act: -0.0001

Data Index: 588853 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1771480 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1506. Min Act: -0.0001

Data Index: 851773 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #19