< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 49 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6936. Min Act: -0.1700

Data Index: 4191804 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6936. Min Act: -0.1700

Data Index: 4033909 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6936. Min Act: -0.1700

Data Index: 9547176 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6936. Min Act: -0.1700

Data Index: 7552223 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6615. Min Act: -0.1700

Data Index: 10329892 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6615. Min Act: -0.1700

Data Index: 3734309 (The Pile)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6455. Min Act: -0.1700

Data Index: 2657922 (The Pile)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6294. Min Act: -0.1700

Data Index: 2226729 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.6134. Min Act: -0.1700

Data Index: 10530461 (The Pile)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5973. Min Act: -0.1700

Data Index: 1253218 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5812. Min Act: -0.1700

Data Index: 2847899 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5812. Min Act: -0.1700

Data Index: 2986438 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5812. Min Act: -0.1700

Data Index: 5876839 (The Pile)

Max Activating Token Index: 932

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5812. Min Act: -0.1700

Data Index: 7050237 (The Pile)

Max Activating Token Index: 968

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5650. Min Act: -0.1700

Data Index: 2066557 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5650. Min Act: -0.1700

Data Index: 9446924 (The Pile)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5650. Min Act: -0.1700

Data Index: 6529210 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5650. Min Act: -0.1700

Data Index: 3510930 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5489. Min Act: -0.1700

Data Index: 3315550 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6936. Min Range: -2.6936

Max Act: 2.5489. Min Act: -0.1700

Data Index: 4098187 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #19