< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 54 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: 0.4590. Min Range: -0.4590

Max Act: 0.4590. Min Act: -0.0001

Data Index: 1047641 (The Pile)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1761930 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4306. Min Act: -0.0001

Data Index: 609592 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4281. Min Act: -0.0001

Data Index: 750253 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4246. Min Act: -0.0001

Data Index: 361002 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1488249 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3875. Min Act: -0.0001

Data Index: 1430061 (The Pile)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4144. Min Act: -0.0001

Data Index: 1898439 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1819915 (The Pile)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4199. Min Act: -0.0001

Data Index: 1927704 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4063. Min Act: -0.0001

Data Index: 199913 (The Pile)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4001. Min Act: -0.0001

Data Index: 944914 (The Pile)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4189. Min Act: -0.0001

Data Index: 204977 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4182. Min Act: -0.0001

Data Index: 1274117 (The Pile)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4024. Min Act: -0.0001

Data Index: 142067 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4115. Min Act: -0.0001

Data Index: 1512992 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3991. Min Act: -0.0001

Data Index: 1505294 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3820. Min Act: -0.0001

Data Index: 1968590 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3722. Min Act: -0.0001

Data Index: 748413 (The Pile)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3975. Min Act: -0.0001

Data Index: 665545 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #19