< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1996 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: 2.8430. Min Range: -2.8430

Max Act: 2.8430. Min Act: -0.1700

Data Index: 1428729 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.8112. Min Act: -0.1700

Data Index: 4044387 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.7314. Min Act: -0.1700

Data Index: 4443077 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.7314. Min Act: -0.1700

Data Index: 2662353 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.7154. Min Act: -0.1700

Data Index: 10442737 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.7154. Min Act: -0.1700

Data Index: 6077343 (The Pile)

Max Activating Token Index: 377

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.7154. Min Act: -0.1700

Data Index: 10074816 (The Pile)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6994. Min Act: -0.1700

Data Index: 8960314 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6994. Min Act: -0.1700

Data Index: 3494025 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6834. Min Act: -0.1700

Data Index: 4178595 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6834. Min Act: -0.1700

Data Index: 6675068 (The Pile)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6674. Min Act: -0.1700

Data Index: 6938488 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6994. Min Act: -0.1700

Data Index: 3721330 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6674. Min Act: -0.1700

Data Index: 7757395 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6674. Min Act: -0.1700

Data Index: 7860011 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6674. Min Act: -0.1700

Data Index: 2305637 (The Pile)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6514. Min Act: -0.1700

Data Index: 7295697 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6514. Min Act: -0.1700

Data Index: 10302474 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6674. Min Act: -0.1700

Data Index: 2113358 (The Pile)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6674. Min Act: -0.1700

Data Index: 10490898 (The Pile)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #19