< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 17 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.3442. Min Act: -0.1700

Data Index: 4262075 (The Pile)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2971. Min Act: -0.1699

Data Index: 4556360 (The Pile)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2657. Min Act: -0.1700

Data Index: 1941398 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2657. Min Act: -0.1699

Data Index: 4029966 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2499. Min Act: -0.1699

Data Index: 5288705 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.2342. Min Act: -0.1700

Data Index: 2999511 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1555. Min Act: -0.1699

Data Index: 3623442 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1555. Min Act: -0.1700

Data Index: 8078856 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.1240. Min Act: -0.1700

Data Index: 9153850 (The Pile)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0925. Min Act: -0.1700

Data Index: 2938912 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0610. Min Act: -0.1699

Data Index: 8008889 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0610. Min Act: -0.1700

Data Index: 4773520 (The Pile)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0610. Min Act: -0.1700

Data Index: 9093453 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0452. Min Act: -0.1700

Data Index: 7422195 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0136. Min Act: -0.1700

Data Index: 616837 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3442. Min Range: -3.3442

Max Act: 3.0136. Min Act: -0.1700

Data Index: 5131975 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9978. Min Act: -0.1700

Data Index: 4612260 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9978. Min Act: -0.1700

Data Index: 3308263 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9978. Min Act: -0.1700

Data Index: 2854756 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3442. Min Range: -3.3442

Max Act: 2.9820. Min Act: -0.1700

Data Index: 7347884 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #19