< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2044 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.9509. Min Act: -0.1700

Data Index: 6123160 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.2634. Min Range: -5.2634

Max Act: 5.2634. Min Act: -0.1700

Data Index: 3598417 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.2634. Min Range: -5.2634

Max Act: 5.1384. Min Act: -0.1700

Data Index: 9343025 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.6853. Min Act: -0.1700

Data Index: 9676905 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.8259. Min Act: -0.1699

Data Index: 2345106 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.8884. Min Act: -0.1700

Data Index: 4991354 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.9196. Min Act: -0.1698

Data Index: 5050360 (The Pile)

Max Activating Token Index: 124

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.9196. Min Act: -0.1699

Data Index: 2845906 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.6540. Min Act: -0.1699

Data Index: 7002308 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.7946. Min Act: -0.1700

Data Index: 4402408 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.9196. Min Act: -0.1699

Data Index: 4801427 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.9509. Min Act: -0.1696

Data Index: 6369453 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.7634. Min Act: -0.1700

Data Index: 3326579 (The Pile)

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.5915. Min Act: -0.1700

Data Index: 6601114 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.6853. Min Act: -0.1679

Data Index: 2112250 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.9821. Min Act: -0.1699

Data Index: 4325220 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.5915. Min Act: -0.1700

Data Index: 1583715 (The Pile)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.7634. Min Act: -0.1700

Data Index: 1933779 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.6227. Min Act: -0.1700

Data Index: 7126170 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.2634. Min Range: -5.2634

Max Act: 4.7165. Min Act: -0.1700

Data Index: 7477970 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #19