< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4082 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.2153. Min Act: -0.1700

Data Index: 7934310 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.2153. Min Act: -0.1700

Data Index: 2756056 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.1996. Min Act: -0.1700

Data Index: 5196019 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.1523. Min Act: -0.1700

Data Index: 940862 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.1366. Min Act: -0.1700

Data Index: 6193324 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.1208. Min Act: -0.1700

Data Index: 6866256 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.1051. Min Act: -0.1700

Data Index: 8882904 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.1051. Min Act: -0.1700

Data Index: 6619154 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0893. Min Act: -0.1700

Data Index: 8889978 (The Pile)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0893. Min Act: -0.1700

Data Index: 4960501 (The Pile)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0735. Min Act: -0.1700

Data Index: 4970670 (The Pile)

Max Activating Token Index: 243

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0735. Min Act: -0.1700

Data Index: 4441087 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0577. Min Act: -0.1700

Data Index: 6310751 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0577. Min Act: -0.1700

Data Index: 5994723 (The Pile)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0577. Min Act: -0.1700

Data Index: 4500113 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0420. Min Act: -0.1700

Data Index: 3711616 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0420. Min Act: -0.1700

Data Index: 4168392 (The Pile)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0262. Min Act: -0.1700

Data Index: 8396510 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0262. Min Act: -0.1700

Data Index: 5850533 (The Pile)

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2153. Min Range: -3.2153

Max Act: 3.0262. Min Act: -0.1700

Data Index: 6910765 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #19