< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3009 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: 1.7459. Min Range: -1.7459

Max Act: 1.7333. Min Act: -0.0001

Data Index: 862202 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.6969. Min Act: -0.0000

Data Index: 835803 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.6872. Min Act: -0.0000

Data Index: 1418677 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.7459. Min Act: -0.0000

Data Index: 461018 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.6365. Min Act: -0.0000

Data Index: 242615 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.6066. Min Act: -0.0000

Data Index: 183666 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4984. Min Act: -0.0001

Data Index: 1270744 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5770. Min Act: -0.0000

Data Index: 659840 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5628. Min Act: -0.0000

Data Index: 1957673 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5196. Min Act: -0.0001

Data Index: 1634313 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1148903 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5045. Min Act: -0.0000

Data Index: 441306 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5124. Min Act: -0.0000

Data Index: 674346 (The Pile)

Max Activating Token Index: 123

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1950174 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1161871 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4471. Min Act: -0.0000

Data Index: 1822217 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4401. Min Act: -0.0000

Data Index: 1249772 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.3667. Min Act: -0.0000

Data Index: 78239 (The Pile)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.5052. Min Act: -0.0001

Data Index: 236617 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7459. Min Range: -1.7459

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1755776 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #19