< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 18 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.5837. Min Act: -0.1700

Data Index: 377740 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.5210. Min Act: -0.1700

Data Index: 2913112 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.4584. Min Act: -0.1700

Data Index: 9569230 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.4427. Min Act: -0.1700

Data Index: 3505461 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.4427. Min Act: -0.1700

Data Index: 4028733 (The Pile)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.4427. Min Act: -0.1700

Data Index: 5751150 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.4270. Min Act: -0.1700

Data Index: 9558628 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3956. Min Act: -0.1700

Data Index: 8320829 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3956. Min Act: -0.1700

Data Index: 3667004 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3956. Min Act: -0.1700

Data Index: 10169076 (The Pile)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3799. Min Act: -0.1700

Data Index: 5371954 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3643. Min Act: -0.1700

Data Index: 9838634 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3643. Min Act: -0.1700

Data Index: 2645026 (The Pile)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3643. Min Act: -0.1700

Data Index: 1198125 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3486. Min Act: -0.1700

Data Index: 4540545 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3329. Min Act: -0.1700

Data Index: 4011710 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3172. Min Act: -0.1700

Data Index: 797706 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3172. Min Act: -0.1700

Data Index: 9113042 (The Pile)

Max Activating Token Index: 990

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3172. Min Act: -0.1700

Data Index: 10534872 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.5837. Min Range: -3.5837

Max Act: 3.3015. Min Act: -0.1700

Data Index: 634405 (The Pile)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #19