< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4032 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0527. Min Range: -3.0527

Max Act: 3.0527. Min Act: -0.1700

Data Index: 6266065 (The Pile)

Max Activating Token Index: 134

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8786. Min Act: -0.1700

Data Index: 2515103 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8627. Min Act: -0.1700

Data Index: 2244859 (The Pile)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8468. Min Act: -0.1700

Data Index: 3807270 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8468. Min Act: -0.1700

Data Index: 1157016 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8468. Min Act: -0.1700

Data Index: 9208755 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8309. Min Act: -0.1700

Data Index: 9981257 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8309. Min Act: -0.1700

Data Index: 8051419 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8309. Min Act: -0.1700

Data Index: 2263943 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8309. Min Act: -0.1700

Data Index: 4226051 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8150. Min Act: -0.1700

Data Index: 4833399 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8150. Min Act: -0.1700

Data Index: 1070235 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.8150. Min Act: -0.1700

Data Index: 2931614 (The Pile)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7991. Min Act: -0.1700

Data Index: 1575365 (The Pile)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7991. Min Act: -0.1700

Data Index: 9714167 (The Pile)

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7831. Min Act: -0.1700

Data Index: 4650749 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7831. Min Act: -0.1700

Data Index: 1856720 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7672. Min Act: -0.1700

Data Index: 6950615 (The Pile)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7672. Min Act: -0.1700

Data Index: 7088824 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0527. Min Range: -3.0527

Max Act: 2.7672. Min Act: -0.1700

Data Index: 2560886 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #19