< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.5038. Min Act: -0.0001

Data Index: 672348 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.5025. Min Act: -0.0001

Data Index: 1902711 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4307. Min Act: -0.0001

Data Index: 1629100 (The Pile)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4121. Min Act: -0.0001

Data Index: 942797 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4343. Min Act: -0.0001

Data Index: 30336 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4552. Min Act: -0.0001

Data Index: 445356 (The Pile)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4486. Min Act: -0.0001

Data Index: 1458061 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4309. Min Act: -0.0001

Data Index: 18943 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4452. Min Act: -0.0001

Data Index: 325443 (The Pile)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3829. Min Act: -0.0001

Data Index: 963630 (The Pile)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3918. Min Act: -0.0001

Data Index: 467121 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4323. Min Act: -0.0001

Data Index: 283867 (The Pile)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4062. Min Act: -0.0001

Data Index: 118603 (The Pile)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4171. Min Act: -0.0001

Data Index: 1440710 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4049. Min Act: -0.0001

Data Index: 921768 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3921. Min Act: -0.0001

Data Index: 1414773 (The Pile)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3957. Min Act: -0.0001

Data Index: 1872211 (The Pile)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.4152. Min Act: -0.0001

Data Index: 1888735 (The Pile)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3958. Min Act: -0.0001

Data Index: 123354 (The Pile)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5038. Min Range: -0.5038

Max Act: 0.3752. Min Act: -0.0001

Data Index: 630764 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #19