< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 3015 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: 0.5824. Min Range: -0.5824

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1888456 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1510784 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5281. Min Act: -0.0000

Data Index: 580574 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1322323 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5395. Min Act: -0.0001

Data Index: 616463 (The Pile)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5151. Min Act: -0.0001

Data Index: 663699 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1896958 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5207. Min Act: -0.0001

Data Index: 468988 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4993. Min Act: -0.0001

Data Index: 1409174 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4992. Min Act: -0.0001

Data Index: 1937279 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5122. Min Act: -0.0001

Data Index: 134490 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4936. Min Act: -0.0001

Data Index: 750277 (The Pile)

Max Activating Token Index: 249

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5086. Min Act: -0.0001

Data Index: 181070 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4939. Min Act: -0.0001

Data Index: 1707537 (The Pile)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5059. Min Act: -0.0000

Data Index: 281941 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4879. Min Act: -0.0000

Data Index: 278955 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4727. Min Act: -0.0001

Data Index: 606034 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4994. Min Act: -0.0001

Data Index: 294841 (The Pile)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4853. Min Act: -0.0001

Data Index: 141245 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1462870 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #19