< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.9084. Min Act: -0.1473

Data Index: 6997882 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.5172. Min Act: -0.1700

Data Index: 6210852 (The Pile)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.4545. Min Act: -0.1700

Data Index: 1615874 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.7833. Min Act: -0.1700

Data Index: 7524462 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.3761. Min Act: -0.1700

Data Index: 6852673 (The Pile)

Max Activating Token Index: 130

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.5015. Min Act: -0.1294

Data Index: 4531541 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.4545. Min Act: -0.1592

Data Index: 5188945 (The Pile)

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.5172. Min Act: -0.1700

Data Index: 4087550 (The Pile)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.2662. Min Act: -0.1700

Data Index: 5240517 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.4075. Min Act: -0.1699

Data Index: 348318 (The Pile)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.6268. Min Act: -0.1698

Data Index: 10570819 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9084. Min Range: -3.9084

Max Act: 2.9192. Min Act: -0.1700

Data Index: 9655832 (The Pile)

Max Activating Token Index: 195

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.4075. Min Act: -0.1699

Data Index: 9533957 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.5329. Min Act: -0.1700

Data Index: 3458362 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.3290. Min Act: -0.1700

Data Index: 3560810 (The Pile)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.6112. Min Act: -0.1700

Data Index: 1973240 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.4702. Min Act: -0.1563

Data Index: 6453538 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.3761. Min Act: -0.1700

Data Index: 1366597 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.3761. Min Act: -0.1699

Data Index: 10188141 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9084. Min Range: -3.9084

Max Act: 3.6425. Min Act: -0.1690

Data Index: 6185976 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #19