< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 31 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0794. Min Act: -0.1700

Data Index: 8432052 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0626. Min Act: -0.1700

Data Index: 6308148 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0626. Min Act: -0.1700

Data Index: 3690037 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0458. Min Act: -0.1700

Data Index: 578637 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0290. Min Act: -0.1700

Data Index: 8034935 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0290. Min Act: -0.1700

Data Index: 6233553 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0290. Min Act: -0.1700

Data Index: 2161506 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0290. Min Act: -0.1700

Data Index: 9029795 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0121. Min Act: -0.1700

Data Index: 6423872 (The Pile)

Max Activating Token Index: 818

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0121. Min Act: -0.1700

Data Index: 6285677 (The Pile)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0121. Min Act: -0.1700

Data Index: 4171290 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0794. Min Range: -2.0794

Max Act: 2.0121. Min Act: -0.1700

Data Index: 1793401 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 2201288 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 5445122 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 9784867 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 10045548 (The Pile)

Max Activating Token Index: 338

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 10503025 (The Pile)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 5599906 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9952. Min Act: -0.1700

Data Index: 8216750 (The Pile)

Max Activating Token Index: 418

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0794. Min Range: -2.0794

Max Act: 1.9783. Min Act: -0.1700

Data Index: 5936132 (The Pile)

Max Activating Token Index: 513

Click toggle to see full text

Truncated

Full Text #19