< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4077 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.7457. Min Act: -0.1700

Data Index: 7765816 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.7457. Min Act: -0.1700

Data Index: 2830866 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.6361. Min Act: -0.1700

Data Index: 3922593 (The Pile)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.6205. Min Act: -0.1700

Data Index: 8001156 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.6048. Min Act: -0.1700

Data Index: 4434947 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.6048. Min Act: -0.1700

Data Index: 3704237 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.6048. Min Act: -0.1700

Data Index: 2559428 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5892. Min Act: -0.1700

Data Index: 2031266 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5735. Min Act: -0.1700

Data Index: 1935310 (The Pile)

Max Activating Token Index: 731

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5735. Min Act: -0.1700

Data Index: 8154782 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5735. Min Act: -0.1700

Data Index: 9952195 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5422. Min Act: -0.1700

Data Index: 6205324 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5422. Min Act: -0.1700

Data Index: 1394165 (The Pile)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.5265. Min Act: -0.1699

Data Index: 10673750 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.4952. Min Act: -0.1700

Data Index: 8942734 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.4952. Min Act: -0.1700

Data Index: 10406407 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.4952. Min Act: -0.1700

Data Index: 6584288 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.4795. Min Act: -0.1700

Data Index: 4351851 (The Pile)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.4795. Min Act: -0.1700

Data Index: 475620 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7457. Min Range: -3.7457

Max Act: 3.4795. Min Act: -0.1700

Data Index: 9465522 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #19