< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 34 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 2.0974. Min Range: -2.0974

Max Act: 2.0974. Min Act: -0.0001

Data Index: 282481 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8118. Min Act: -0.0001

Data Index: 214964 (The Pile)

Max Activating Token Index: 124

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.7423. Min Act: -0.0001

Data Index: 800114 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.7249. Min Act: -0.0001

Data Index: 1050092 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8097. Min Act: -0.0001

Data Index: 1251878 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8571. Min Act: -0.0001

Data Index: 406495 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8848. Min Act: -0.0002

Data Index: 939580 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8326. Min Act: -0.0001

Data Index: 1389197 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8259. Min Act: -0.0002

Data Index: 1030410 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8322. Min Act: -0.0002

Data Index: 741041 (The Pile)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8284. Min Act: -0.0001

Data Index: 524525 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.7793. Min Act: -0.0001

Data Index: 1383120 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.7735. Min Act: -0.0001

Data Index: 717222 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8207. Min Act: -0.0001

Data Index: 18160 (The Pile)

Max Activating Token Index: 769

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8660. Min Act: -0.0001

Data Index: 526879 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8179. Min Act: -0.0001

Data Index: 30425 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.8063. Min Act: -0.0001

Data Index: 64 (The Pile)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.7516. Min Act: -0.0002

Data Index: 1127534 (The Pile)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.7367. Min Act: -0.0001

Data Index: 1712370 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0974. Min Range: -2.0974

Max Act: 1.6851. Min Act: -0.0002

Data Index: 995252 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #19