< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 37 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: 0.1811. Min Range: -0.1811

Max Act: 0.1811. Min Act: -0.0001

Data Index: 1171926 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1124. Min Act: -0.0001

Data Index: 233514 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1860485 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1558129 (The Pile)

Max Activating Token Index: 676

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1337. Min Act: -0.0001

Data Index: 387480 (The Pile)

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1386429 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1794569 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1084. Min Act: -0.0001

Data Index: 525751 (The Pile)

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1167. Min Act: -0.0001

Data Index: 982874 (The Pile)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1020. Min Act: -0.0001

Data Index: 56529 (The Pile)

Max Activating Token Index: 853

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1019. Min Act: -0.0001

Data Index: 194080 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1090. Min Act: -0.0001

Data Index: 81279 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1726125 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1813650 (The Pile)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1215. Min Act: -0.0001

Data Index: 706068 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1209641 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1446702 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0985. Min Act: -0.0001

Data Index: 909470 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1556904 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1811. Min Range: -0.1811

Max Act: 0.0996. Min Act: -0.0001

Data Index: 1863434 (The Pile)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #19