< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4064 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.0673. Min Range: -8.0673

Max Act: 8.0673. Min Act: -0.1699

Data Index: 7977650 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.8798. Min Act: -0.1699

Data Index: 9937873 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.7860. Min Act: -0.1699

Data Index: 8266663 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.7235. Min Act: -0.1700

Data Index: 931770 (The Pile)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6923. Min Act: -0.1699

Data Index: 3475249 (The Pile)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6923. Min Act: -0.1700

Data Index: 7118750 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6610. Min Act: -0.1700

Data Index: 6968967 (The Pile)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6610. Min Act: -0.1700

Data Index: 2425150 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6610. Min Act: -0.1700

Data Index: 4847182 (The Pile)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6610. Min Act: -0.1700

Data Index: 1208182 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6298. Min Act: -0.1700

Data Index: 6746858 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.6298. Min Act: -0.1700

Data Index: 10158339 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5985. Min Act: -0.1700

Data Index: 8532948 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5985. Min Act: -0.1700

Data Index: 1601607 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5673. Min Act: -0.1700

Data Index: 7616590 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5673. Min Act: -0.1700

Data Index: 1684979 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5673. Min Act: -0.1699

Data Index: 6431827 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5360. Min Act: -0.1700

Data Index: 8044789 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5360. Min Act: -0.1700

Data Index: 9092537 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.0673. Min Range: -8.0673

Max Act: 7.5360. Min Act: -0.1700

Data Index: 6473785 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #19