< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 252 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: 0.6805. Min Range: -0.6805

Max Act: 0.6805. Min Act: 0.0000

Data Index: 1389106 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1319215 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1991409 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1261030 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1595353 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1819719 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5041. Min Act: 0.0000

Data Index: 410062 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5039. Min Act: -0.0000

Data Index: 756072 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5174. Min Act: -0.0000

Data Index: 774345 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1737968 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.5119. Min Act: -0.0000

Data Index: 500407 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4894. Min Act: -0.0000

Data Index: 396604 (The Pile)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4976. Min Act: -0.0000

Data Index: 347724 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4936. Min Act: 0.0000

Data Index: 801414 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4672. Min Act: 0.0000

Data Index: 1580434 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4439. Min Act: -0.0000

Data Index: 509291 (The Pile)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4685. Min Act: -0.0000

Data Index: 322206 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1102650 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4451. Min Act: -0.0000

Data Index: 784211 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.6805. Min Range: -0.6805

Max Act: 0.4754. Min Act: -0.0000

Data Index: 495538 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #19