< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 18 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.4027. Min Act: -0.0001

Data Index: 80759 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1112946 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3928. Min Act: -0.0001

Data Index: 647474 (The Pile)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3912. Min Act: -0.0001

Data Index: 1488085 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3695. Min Act: -0.0001

Data Index: 998621 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3668. Min Act: -0.0001

Data Index: 560234 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3794. Min Act: -0.0001

Data Index: 678278 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3716. Min Act: -0.0001

Data Index: 1854448 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3564. Min Act: -0.0001

Data Index: 670077 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3539. Min Act: -0.0001

Data Index: 1059144 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3528. Min Act: -0.0001

Data Index: 755090 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3347. Min Act: -0.0001

Data Index: 464217 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3561. Min Act: -0.0001

Data Index: 1469268 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3363. Min Act: -0.0001

Data Index: 1849894 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3349. Min Act: -0.0001

Data Index: 1439757 (The Pile)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3416. Min Act: -0.0001

Data Index: 1233949 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3728. Min Act: -0.0001

Data Index: 167716 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3603. Min Act: -0.0001

Data Index: 1319729 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3569. Min Act: -0.0001

Data Index: 1448052 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3254. Min Act: -0.0001

Data Index: 1711341 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #19