< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 42 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: 3.8809. Min Range: -3.8809

Max Act: 3.8809. Min Act: -0.1700

Data Index: 2606105 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8809. Min Act: -0.1700

Data Index: 7828256 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8497. Min Act: -0.1700

Data Index: 7239706 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8340. Min Act: -0.1700

Data Index: 10544974 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8497. Min Act: -0.1700

Data Index: 6985367 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8340. Min Act: -0.1700

Data Index: 3543117 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8184. Min Act: -0.1700

Data Index: 9960577 (The Pile)

Max Activating Token Index: 23

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8028. Min Act: -0.1700

Data Index: 8311990 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8184. Min Act: -0.1700

Data Index: 4340615 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7871. Min Act: -0.1700

Data Index: 235663 (The Pile)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7871. Min Act: -0.1700

Data Index: 149656 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.8028. Min Act: -0.1700

Data Index: 10296467 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7715. Min Act: -0.1700

Data Index: 7997811 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7402. Min Act: -0.1700

Data Index: 7703947 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7715. Min Act: -0.1700

Data Index: 2901050 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7715. Min Act: -0.1700

Data Index: 7246834 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7402. Min Act: -0.1700

Data Index: 3107289 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7402. Min Act: -0.1700

Data Index: 4822209 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1765095 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8809. Min Range: -3.8809

Max Act: 3.7402. Min Act: -0.1700

Data Index: 7547516 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #19