< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4066 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.4817. Min Act: -0.1700

Data Index: 4285756 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.4817. Min Act: -0.1700

Data Index: 9970763 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.4504. Min Act: -0.1700

Data Index: 4406253 (The Pile)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.4190. Min Act: -0.1700

Data Index: 9314183 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.4033. Min Act: -0.1700

Data Index: 2307186 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3877. Min Act: -0.1700

Data Index: 6105862 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3877. Min Act: -0.1700

Data Index: 3984973 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3720. Min Act: -0.1700

Data Index: 9775665 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3563. Min Act: -0.1700

Data Index: 2820750 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3563. Min Act: -0.1700

Data Index: 3146590 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3563. Min Act: -0.1700

Data Index: 6079798 (The Pile)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3563. Min Act: -0.1700

Data Index: 9676967 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3563. Min Act: -0.1700

Data Index: 9537188 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3406. Min Act: -0.1700

Data Index: 9339103 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3249. Min Act: -0.1700

Data Index: 1443151 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3249. Min Act: -0.1700

Data Index: 5088179 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3249. Min Act: -0.1700

Data Index: 3772042 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3249. Min Act: -0.1700

Data Index: 4589821 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3249. Min Act: -0.1700

Data Index: 6151779 (The Pile)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4817. Min Range: -3.4817

Max Act: 3.3249. Min Act: -0.1700

Data Index: 6388030 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #19