< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 21 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3410. Min Act: -0.1700

Data Index: 826835 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.3253. Min Act: -0.1700

Data Index: 10163093 (The Pile)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2939. Min Act: -0.1700

Data Index: 6969621 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2939. Min Act: -0.1700

Data Index: 5891230 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2782. Min Act: -0.1700

Data Index: 9645598 (The Pile)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2624. Min Act: -0.1700

Data Index: 8061673 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2624. Min Act: -0.1700

Data Index: 9422785 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2467. Min Act: -0.1700

Data Index: 2298775 (The Pile)

Max Activating Token Index: 838

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2310. Min Act: -0.1700

Data Index: 1517089 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2310. Min Act: -0.1700

Data Index: 1794673 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2310. Min Act: -0.1700

Data Index: 7361698 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2310. Min Act: -0.1700

Data Index: 2262395 (The Pile)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2310. Min Act: -0.1700

Data Index: 8204867 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2153. Min Act: -0.1700

Data Index: 8642235 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.2153. Min Act: -0.1700

Data Index: 209638 (The Pile)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1995. Min Act: -0.1700

Data Index: 7571108 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1995. Min Act: -0.1700

Data Index: 1808558 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1995. Min Act: -0.1700

Data Index: 6287747 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1995. Min Act: -0.1700

Data Index: 9164102 (The Pile)

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3410. Min Range: -3.3410

Max Act: 3.1995. Min Act: -0.1700

Data Index: 3899881 (The Pile)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #19