< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2016 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.3288. Min Act: -0.1700

Data Index: 10376308 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.2975. Min Act: -0.1700

Data Index: 1403807 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.2975. Min Act: -0.1700

Data Index: 387598 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.2037. Min Act: -0.1700

Data Index: 7086902 (The Pile)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.2037. Min Act: -0.1700

Data Index: 948275 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.1412. Min Act: -0.1700

Data Index: 10130926 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0787. Min Act: -0.1700

Data Index: 333981 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0787. Min Act: -0.1700

Data Index: 3704116 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0474. Min Act: -0.1700

Data Index: 6424989 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0474. Min Act: -0.1700

Data Index: 10427061 (The Pile)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0474. Min Act: -0.1700

Data Index: 9489369 (The Pile)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0162. Min Act: -0.1700

Data Index: 5325133 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3288. Min Range: -4.3288

Max Act: 3.9849. Min Act: -0.1700

Data Index: 253631 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0162. Min Act: -0.1700

Data Index: 8781033 (The Pile)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0162. Min Act: -0.1700

Data Index: 5004078 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0162. Min Act: -0.1700

Data Index: 4818288 (The Pile)

Max Activating Token Index: 995

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3288. Min Range: -4.3288

Max Act: 4.0162. Min Act: -0.1700

Data Index: 6706522 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3288. Min Range: -4.3288

Max Act: 3.9849. Min Act: -0.1700

Data Index: 5759929 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3288. Min Range: -4.3288

Max Act: 3.9849. Min Act: -0.1700

Data Index: 555413 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3288. Min Range: -4.3288

Max Act: 3.9536. Min Act: -0.1700

Data Index: 6476821 (The Pile)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #19