< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 52 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1003. Min Range: -3.1003

Max Act: 3.1003. Min Act: -0.1700

Data Index: 5410837 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1003. Min Range: -3.1003

Max Act: 3.0529. Min Act: -0.1700

Data Index: 10762061 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1003. Min Range: -3.1003

Max Act: 3.0371. Min Act: -0.1700

Data Index: 8628057 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1003. Min Range: -3.1003

Max Act: 3.0055. Min Act: -0.1700

Data Index: 6266445 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9897. Min Act: -0.1700

Data Index: 9204678 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9897. Min Act: -0.1700

Data Index: 8672237 (The Pile)

Max Activating Token Index: 339

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 619400 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 7929696 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 5111830 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 5221406 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 933721 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 4826428 (The Pile)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9739. Min Act: -0.1700

Data Index: 8797969 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 3117795 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 2159453 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 6941693 (The Pile)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 5193346 (The Pile)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 5095404 (The Pile)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 1815020 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1003. Min Range: -3.1003

Max Act: 2.9581. Min Act: -0.1700

Data Index: 6191592 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #19