< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 8 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: 3.4258. Min Range: -3.4258

Max Act: 3.4258. Min Act: -0.1700

Data Index: 3081881 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.3630. Min Act: -0.1700

Data Index: 6196944 (The Pile)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.3316. Min Act: -0.1700

Data Index: 7960503 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.3002. Min Act: -0.1700

Data Index: 8990654 (The Pile)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.3002. Min Act: -0.1700

Data Index: 6408058 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1902. Min Act: -0.1700

Data Index: 10758927 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1902. Min Act: -0.1700

Data Index: 705595 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1902. Min Act: -0.1700

Data Index: 891651 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1744. Min Act: -0.1700

Data Index: 8236001 (The Pile)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1587. Min Act: -0.1700

Data Index: 162610 (The Pile)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1587. Min Act: -0.1700

Data Index: 3923552 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1429. Min Act: -0.1700

Data Index: 2878460 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1429. Min Act: -0.1700

Data Index: 8889757 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1272. Min Act: -0.1700

Data Index: 1530611 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1272. Min Act: -0.1700

Data Index: 5267186 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.1272. Min Act: -0.1700

Data Index: 10001451 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.0957. Min Act: -0.1700

Data Index: 4224161 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.0957. Min Act: -0.1700

Data Index: 7855649 (The Pile)

Max Activating Token Index: 733

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.0957. Min Act: -0.1700

Data Index: 2281859 (The Pile)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4258. Min Range: -3.4258

Max Act: 3.0957. Min Act: -0.1700

Data Index: 8167348 (The Pile)

Max Activating Token Index: 724

Click toggle to see full text

Truncated

Full Text #19