< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1995 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2850. Min Act: -0.1700

Data Index: 6772781 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2932. Min Act: -0.1700

Data Index: 394308 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.3015. Min Act: -0.1700

Data Index: 530390 (The Pile)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2685. Min Act: -0.1700

Data Index: 8932281 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.3261. Min Act: -0.1700

Data Index: 9062221 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2850. Min Act: -0.1700

Data Index: 2048278 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.3015. Min Act: -0.1700

Data Index: 2525880 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2850. Min Act: -0.1700

Data Index: 9842974 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2768. Min Act: -0.1700

Data Index: 2002609 (The Pile)

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2685. Min Act: -0.1700

Data Index: 7098839 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2850. Min Act: -0.1700

Data Index: 777193 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2685. Min Act: -0.1699

Data Index: 237837 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2355. Min Act: -0.1700

Data Index: 2095443 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2438. Min Act: -0.1695

Data Index: 8588268 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2768. Min Act: -0.1698

Data Index: 3429136 (The Pile)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2438. Min Act: -0.1700

Data Index: 6315608 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2355. Min Act: -0.1700

Data Index: 2802188 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2107. Min Act: -0.1440

Data Index: 2124930 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2272. Min Act: -0.1700

Data Index: 3494593 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3261. Min Range: -2.3261

Max Act: 2.2355. Min Act: -0.1646

Data Index: 9688186 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #19