< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3 in Layer 19

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.4203. Min Act: -0.1700

Data Index: 5259955 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3889. Min Act: -0.1700

Data Index: 10037970 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3889. Min Act: -0.1700

Data Index: 8254148 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3262. Min Act: -0.1700

Data Index: 7615537 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3105. Min Act: -0.1700

Data Index: 3251100 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2948. Min Act: -0.1700

Data Index: 5817595 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2791. Min Act: -0.1700

Data Index: 7064775 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2633. Min Act: -0.1700

Data Index: 10111905 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2633. Min Act: -0.1700

Data Index: 173491 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2633. Min Act: -0.1700

Data Index: 10573791 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2319. Min Act: -0.1700

Data Index: 350977 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2319. Min Act: -0.1700

Data Index: 8397268 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2319. Min Act: -0.1700

Data Index: 5559049 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2319. Min Act: -0.1700

Data Index: 1301057 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2162. Min Act: -0.1700

Data Index: 1156006 (The Pile)

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2162. Min Act: -0.1700

Data Index: 7818573 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2162. Min Act: -0.1700

Data Index: 1344761 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2162. Min Act: -0.1700

Data Index: 9471059 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2004. Min Act: -0.1700

Data Index: 1257096 (The Pile)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2004. Min Act: -0.1700

Data Index: 7629993 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #19