< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 49 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1311. Min Range: -3.1311

Max Act: 3.1311. Min Act: -0.1700

Data Index: 3980458 (The Pile)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1311. Min Range: -3.1311

Max Act: 3.0838. Min Act: -0.1700

Data Index: 6633010 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1311. Min Range: -3.1311

Max Act: 3.0838. Min Act: -0.1700

Data Index: 3859239 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1311. Min Range: -3.1311

Max Act: 3.0048. Min Act: -0.1700

Data Index: 1363726 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9415. Min Act: -0.1700

Data Index: 7359195 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9415. Min Act: -0.1700

Data Index: 5694420 (The Pile)

Max Activating Token Index: 74

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9257. Min Act: -0.1700

Data Index: 557330 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9257. Min Act: -0.1700

Data Index: 4046358 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9098. Min Act: -0.1700

Data Index: 2511133 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9098. Min Act: -0.1700

Data Index: 9572970 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.9098. Min Act: -0.1700

Data Index: 7913723 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8940. Min Act: -0.1700

Data Index: 7812304 (The Pile)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8940. Min Act: -0.1700

Data Index: 5425897 (The Pile)

Max Activating Token Index: 163

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8940. Min Act: -0.1700

Data Index: 3619813 (The Pile)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8940. Min Act: -0.1700

Data Index: 6027225 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8940. Min Act: -0.1700

Data Index: 5039064 (The Pile)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8781. Min Act: -0.1700

Data Index: 5704717 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8781. Min Act: -0.1700

Data Index: 4167763 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8781. Min Act: -0.1700

Data Index: 2683079 (The Pile)

Max Activating Token Index: 921

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1311. Min Range: -3.1311

Max Act: 2.8781. Min Act: -0.1700

Data Index: 543370 (The Pile)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #19