< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4069 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.3181. Min Act: -0.1700

Data Index: 10261116 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.2555. Min Act: -0.1700

Data Index: 6859649 (The Pile)

Max Activating Token Index: 804

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.1618. Min Act: -0.1700

Data Index: 1015599 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.1618. Min Act: -0.1700

Data Index: 3430468 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.1305. Min Act: -0.1700

Data Index: 2456551 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.0367. Min Act: -0.1700

Data Index: 4170335 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.0211. Min Act: -0.1700

Data Index: 3384440 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3181. Min Range: -4.3181

Max Act: 4.0055. Min Act: -0.1700

Data Index: 3991738 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9742. Min Act: -0.1700

Data Index: 3733554 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9586. Min Act: -0.1700

Data Index: 4050110 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9273. Min Act: -0.1700

Data Index: 4426519 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9273. Min Act: -0.1700

Data Index: 1848585 (The Pile)

Max Activating Token Index: 1004

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9273. Min Act: -0.1700

Data Index: 8393360 (The Pile)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9273. Min Act: -0.1700

Data Index: 6037724 (The Pile)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9117. Min Act: -0.1700

Data Index: 2094275 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9117. Min Act: -0.1700

Data Index: 9674551 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9117. Min Act: -0.1700

Data Index: 2972879 (The Pile)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9117. Min Act: -0.1700

Data Index: 4780655 (The Pile)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.9117. Min Act: -0.1700

Data Index: 1503393 (The Pile)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3181. Min Range: -4.3181

Max Act: 3.8960. Min Act: -0.1700

Data Index: 5126493 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #19