< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 52 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.3807. Min Act: -0.1700

Data Index: 1913282 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.3336. Min Act: -0.1700

Data Index: 5579286 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.3179. Min Act: -0.1700

Data Index: 6299932 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.3022. Min Act: -0.1700

Data Index: 1643240 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.3022. Min Act: -0.1700

Data Index: 6299344 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2865. Min Act: -0.1700

Data Index: 4344304 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2708. Min Act: -0.1700

Data Index: 5248128 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2394. Min Act: -0.1700

Data Index: 1953782 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2394. Min Act: -0.1700

Data Index: 6767346 (The Pile)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2394. Min Act: -0.1700

Data Index: 2935241 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2236. Min Act: -0.1700

Data Index: 5832721 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2236. Min Act: -0.1700

Data Index: 1802964 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2079. Min Act: -0.1700

Data Index: 1545361 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2079. Min Act: -0.1700

Data Index: 6128799 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2079. Min Act: -0.1700

Data Index: 10543774 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2079. Min Act: -0.1700

Data Index: 10009516 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2079. Min Act: -0.1700

Data Index: 9929693 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.2079. Min Act: -0.1700

Data Index: 6363101 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.1922. Min Act: -0.1700

Data Index: 7409242 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3807. Min Range: -3.3807

Max Act: 3.1922. Min Act: -0.1700

Data Index: 5166770 (The Pile)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #19