< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4056 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8932. Min Act: -0.1700

Data Index: 2741472 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8775. Min Act: -0.1700

Data Index: 2974939 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8619. Min Act: -0.1700

Data Index: 3514266 (The Pile)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8619. Min Act: -0.1700

Data Index: 2452375 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8462. Min Act: -0.1700

Data Index: 4322723 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8462. Min Act: -0.1700

Data Index: 8479322 (The Pile)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8306. Min Act: -0.1700

Data Index: 2762319 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8306. Min Act: -0.1700

Data Index: 721372 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8150. Min Act: -0.1700

Data Index: 8486935 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8150. Min Act: -0.1700

Data Index: 7893284 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8150. Min Act: -0.1700

Data Index: 8311828 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8150. Min Act: -0.1699

Data Index: 459757 (The Pile)

Max Activating Token Index: 858

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.8150. Min Act: -0.1700

Data Index: 9737373 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7993. Min Act: -0.1700

Data Index: 3493352 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7993. Min Act: -0.1700

Data Index: 530022 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7993. Min Act: -0.1700

Data Index: 7898072 (The Pile)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7837. Min Act: -0.1700

Data Index: 73511 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7680. Min Act: -0.1700

Data Index: 7264894 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7680. Min Act: -0.1700

Data Index: 4880827 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8932. Min Range: -3.8932

Max Act: 3.7680. Min Act: -0.1700

Data Index: 10438765 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #19