< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3058 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2505. Min Act: 0.0000

Data Index: 717235 (The Pile)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1932698 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2262. Min Act: -0.0000

Data Index: 884703 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1766541 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2228. Min Act: 0.0000

Data Index: 1065172 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2214. Min Act: -0.0001

Data Index: 1058813 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1543662 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1504625 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2200. Min Act: -0.0001

Data Index: 526796 (The Pile)

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2086. Min Act: -0.0000

Data Index: 918925 (The Pile)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1542512 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2062. Min Act: -0.0001

Data Index: 44121 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2111. Min Act: -0.0001

Data Index: 169248 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1910354 (The Pile)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2068. Min Act: -0.0001

Data Index: 1902894 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2083. Min Act: -0.0001

Data Index: 52323 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1058673 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1712966 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1977. Min Act: -0.0000

Data Index: 182176 (The Pile)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2505. Min Range: -0.2505

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1307139 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #19