< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.0672. Min Range: -1.0672

Max Act: 1.0148. Min Act: -0.0001

Data Index: 625942 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0672. Min Range: -1.0672

Max Act: 1.0672. Min Act: -0.0001

Data Index: 1812415 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0672. Min Range: -1.0672

Max Act: 1.0346. Min Act: -0.0001

Data Index: 1928215 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0672. Min Range: -1.0672

Max Act: 1.0312. Min Act: -0.0001

Data Index: 929031 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0672. Min Range: -1.0672

Max Act: 1.0020. Min Act: -0.0001

Data Index: 806966 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9232. Min Act: -0.0001

Data Index: 1294494 (The Pile)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9251. Min Act: -0.0001

Data Index: 37700 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9936. Min Act: -0.0001

Data Index: 140366 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8999. Min Act: -0.0001

Data Index: 697270 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1970877 (The Pile)

Max Activating Token Index: 643

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8290. Min Act: -0.0001

Data Index: 788716 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1951385 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8870. Min Act: -0.0001

Data Index: 1369005 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9074. Min Act: -0.0001

Data Index: 1619066 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9464. Min Act: -0.0001

Data Index: 569930 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9782. Min Act: -0.0001

Data Index: 755432 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.9205. Min Act: -0.0001

Data Index: 58900 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1388225 (The Pile)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8504. Min Act: -0.0001

Data Index: 1540137 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0672. Min Range: -1.0672

Max Act: 0.8122. Min Act: -0.0001

Data Index: 436673 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #19