< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 48 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.4107. Min Act: -0.1700

Data Index: 7981264 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3636. Min Act: -0.1700

Data Index: 2172509 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3479. Min Act: -0.1700

Data Index: 3981087 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3322. Min Act: -0.1700

Data Index: 10154247 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3165. Min Act: -0.1700

Data Index: 4193930 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3008. Min Act: -0.1700

Data Index: 10725072 (The Pile)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3008. Min Act: -0.1700

Data Index: 100048 (The Pile)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3008. Min Act: -0.1700

Data Index: 7688411 (The Pile)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.3008. Min Act: -0.1700

Data Index: 153419 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2851. Min Act: -0.1700

Data Index: 8891360 (The Pile)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2851. Min Act: -0.1700

Data Index: 2947964 (The Pile)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2851. Min Act: -0.1700

Data Index: 4662091 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2694. Min Act: -0.1700

Data Index: 3207723 (The Pile)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2694. Min Act: -0.1700

Data Index: 2223715 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2537. Min Act: -0.1700

Data Index: 4521428 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2380. Min Act: -0.1700

Data Index: 912591 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2380. Min Act: -0.1700

Data Index: 8857401 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2380. Min Act: -0.1700

Data Index: 114020 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2223. Min Act: -0.1700

Data Index: 8335321 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4107. Min Range: -3.4107

Max Act: 3.2223. Min Act: -0.1700

Data Index: 8299098 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #19