< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2020 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0470. Min Act: -0.1700

Data Index: 3701856 (The Pile)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0470. Min Act: -0.1700

Data Index: 5348516 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.1408. Min Act: -0.1700

Data Index: 8282970 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.2033. Min Act: -0.1700

Data Index: 5832865 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.9845. Min Act: -0.1700

Data Index: 6662103 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.2658. Min Act: -0.1700

Data Index: 7824991 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0783. Min Act: -0.1700

Data Index: 7196310 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.9532. Min Act: -0.1700

Data Index: 10378392 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.9845. Min Act: -0.1700

Data Index: 2387248 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0470. Min Act: -0.1700

Data Index: 9416657 (The Pile)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0783. Min Act: -0.1700

Data Index: 7340014 (The Pile)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0783. Min Act: -0.1700

Data Index: 3291690 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.8907. Min Act: -0.1700

Data Index: 9702511 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0158. Min Act: -0.1700

Data Index: 9614695 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0783. Min Act: -0.1700

Data Index: 9312587 (The Pile)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.1408. Min Act: -0.1700

Data Index: 9056735 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.1095. Min Act: -0.1700

Data Index: 8941297 (The Pile)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.2658. Min Range: -4.2658

Max Act: 3.8907. Min Act: -0.1700

Data Index: 724949 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.1095. Min Act: -0.1700

Data Index: 510946 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.2658. Min Range: -4.2658

Max Act: 4.0470. Min Act: -0.1700

Data Index: 3634490 (The Pile)

Max Activating Token Index: 855

Click toggle to see full text

Truncated

Full Text #19