< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 13 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: 3.0364. Min Range: -3.0364

Max Act: 3.0364. Min Act: -0.1700

Data Index: 3311273 (The Pile)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9889. Min Act: -0.1700

Data Index: 4994579 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9573. Min Act: -0.1700

Data Index: 358132 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9256. Min Act: -0.1700

Data Index: 1337207 (The Pile)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9415. Min Act: -0.1700

Data Index: 2141081 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9098. Min Act: -0.1700

Data Index: 9219025 (The Pile)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8939. Min Act: -0.1700

Data Index: 3884848 (The Pile)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9098. Min Act: -0.1700

Data Index: 3332587 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8939. Min Act: -0.1700

Data Index: 1181196 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9098. Min Act: -0.1700

Data Index: 5217559 (The Pile)

Max Activating Token Index: 138

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9098. Min Act: -0.1700

Data Index: 7651944 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8780. Min Act: -0.1700

Data Index: 431327 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8939. Min Act: -0.1700

Data Index: 1081581 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8780. Min Act: -0.1700

Data Index: 6261571 (The Pile)

Max Activating Token Index: 166

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8780. Min Act: -0.1700

Data Index: 8811133 (The Pile)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8780. Min Act: -0.1700

Data Index: 7612343 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9256. Min Act: -0.1700

Data Index: 351820 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.9098. Min Act: -0.1700

Data Index: 7382210 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8780. Min Act: -0.1700

Data Index: 6836215 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0364. Min Range: -3.0364

Max Act: 2.8622. Min Act: -0.1700

Data Index: 1461235 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #19