< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7722. Min Act: -0.1700

Data Index: 3343119 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7722. Min Act: -0.1700

Data Index: 2400473 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7722. Min Act: -0.1700

Data Index: 3950628 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7563. Min Act: -0.1700

Data Index: 4535798 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7563. Min Act: -0.1700

Data Index: 7817833 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7563. Min Act: -0.1700

Data Index: 1237245 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7403. Min Act: -0.1700

Data Index: 2875143 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7403. Min Act: -0.1700

Data Index: 9558048 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 8191816 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 116949 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 3177429 (The Pile)

Max Activating Token Index: 628

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 6259752 (The Pile)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7084. Min Act: -0.1700

Data Index: 3071435 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 4082215 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7084. Min Act: -0.1700

Data Index: 6245223 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 9892640 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 434882 (The Pile)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 3593355 (The Pile)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7243. Min Act: -0.1700

Data Index: 3850577 (The Pile)

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.7722. Min Range: -2.7722

Max Act: 2.7084. Min Act: -0.1700

Data Index: 1368656 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #19