< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 23 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.0661. Min Range: -4.0661

Max Act: 4.0036. Min Act: -0.1700

Data Index: 8505515 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.6595. Min Act: -0.1700

Data Index: 6295447 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8160. Min Act: -0.1700

Data Index: 1212157 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8473. Min Act: -0.1700

Data Index: 8502231 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0661. Min Range: -4.0661

Max Act: 4.0661. Min Act: -0.1700

Data Index: 6521212 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9411. Min Act: -0.1700

Data Index: 9694009 (The Pile)

Max Activating Token Index: 692

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8785. Min Act: -0.1700

Data Index: 6837907 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8473. Min Act: -0.1700

Data Index: 5155468 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9411. Min Act: -0.1700

Data Index: 10680675 (The Pile)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.7221. Min Act: -0.1700

Data Index: 8860430 (The Pile)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9411. Min Act: -0.1700

Data Index: 1177243 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9723. Min Act: -0.1700

Data Index: 3471212 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9411. Min Act: -0.1700

Data Index: 9983810 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8473. Min Act: -0.1700

Data Index: 9876693 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9411. Min Act: -0.1700

Data Index: 7635662 (The Pile)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.9723. Min Act: -0.1700

Data Index: 9865953 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8473. Min Act: -0.1700

Data Index: 1489113 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8160. Min Act: -0.1700

Data Index: 3028593 (The Pile)

Max Activating Token Index: 115

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8473. Min Act: -0.1700

Data Index: 1201997 (The Pile)

Max Activating Token Index: 499

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0661. Min Range: -4.0661

Max Act: 3.8473. Min Act: -0.1700

Data Index: 8949600 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #19