< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 60 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.3064. Min Act: -0.1700

Data Index: 3424655 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.3064. Min Act: -0.1700

Data Index: 10734450 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.3064. Min Act: -0.1700

Data Index: 8232867 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.2593. Min Act: -0.1700

Data Index: 1087007 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.2593. Min Act: -0.1700

Data Index: 8594116 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.2593. Min Act: -0.1700

Data Index: 2274037 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.2593. Min Act: -0.1700

Data Index: 3505008 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.2593. Min Act: -0.1700

Data Index: 7688634 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1649. Min Act: -0.1700

Data Index: 10441886 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1649. Min Act: -0.1700

Data Index: 7361207 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1649. Min Act: -0.1700

Data Index: 4229768 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1649. Min Act: -0.1700

Data Index: 379935 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1492. Min Act: -0.1700

Data Index: 9737414 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1492. Min Act: -0.1700

Data Index: 6159801 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1492. Min Act: -0.1700

Data Index: 5746663 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1334. Min Act: -0.1700

Data Index: 8555320 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1334. Min Act: -0.1700

Data Index: 5060052 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1334. Min Act: -0.1700

Data Index: 970888 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1334. Min Act: -0.1700

Data Index: 9108840 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3064. Min Range: -3.3064

Max Act: 3.1334. Min Act: -0.1700

Data Index: 9267149 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #19