< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4049 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.8314. Min Range: -1.8314

Max Act: 1.8314. Min Act: -0.0001

Data Index: 1532312 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.8314. Min Range: -1.8314

Max Act: 1.4863. Min Act: -0.0001

Data Index: 365677 (The Pile)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.9665. Min Act: -0.0001

Data Index: 40053 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.9576. Min Act: -0.0001

Data Index: 726531 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.9949. Min Act: -0.0001

Data Index: 1788783 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.9531. Min Act: -0.0001

Data Index: 907153 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.8314. Min Range: -1.8314

Max Act: 1.1018. Min Act: -0.0001

Data Index: 818791 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.9586. Min Act: -0.0001

Data Index: 892446 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8408. Min Act: -0.0001

Data Index: 1319104 (The Pile)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.9446. Min Act: -0.0001

Data Index: 469635 (The Pile)

Max Activating Token Index: 31

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1519626 (The Pile)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8231. Min Act: -0.0001

Data Index: 1305236 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8992. Min Act: -0.0001

Data Index: 1572078 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8631. Min Act: -0.0001

Data Index: 1984718 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1687871 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8140. Min Act: -0.0001

Data Index: 228337 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8492. Min Act: -0.0000

Data Index: 764637 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.7954. Min Act: -0.0001

Data Index: 386341 (The Pile)

Max Activating Token Index: 639

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8742. Min Act: -0.0001

Data Index: 1299995 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.8314. Min Range: -1.8314

Max Act: 0.8857. Min Act: -0.0001

Data Index: 994063 (The Pile)

Max Activating Token Index: 59

Click toggle to see full text

Truncated

Full Text #19