< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6397 in Layer 27

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 11.0680. Min Range: -11.0680

Max Act: 11.0680. Min Act: -0.1700

Data Index: 3403717 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.8805. Min Act: -0.1700

Data Index: 4095309 (Open Web Text)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.7555. Min Act: -0.1700

Data Index: 8216917 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.7555. Min Act: -0.1700

Data Index: 4727252 (Open Web Text)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.6305. Min Act: -0.1700

Data Index: 7955021 (Open Web Text)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.6305. Min Act: -0.1700

Data Index: 58614 (Open Web Text)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.5680. Min Act: -0.1700

Data Index: 4077996 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.5680. Min Act: -0.1700

Data Index: 7952524 (Open Web Text)

Max Activating Token Index: 775

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.3180. Min Act: -0.1700

Data Index: 1340383 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.3180. Min Act: -0.1700

Data Index: 2173473 (Open Web Text)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.2555. Min Act: -0.1700

Data Index: 4439175 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1930. Min Act: -0.1700

Data Index: 8581193 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1930. Min Act: -0.1700

Data Index: 4701785 (Open Web Text)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1930. Min Act: -0.1700

Data Index: 6449939 (Open Web Text)

Max Activating Token Index: 236

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1930. Min Act: -0.1700

Data Index: 3732711 (Open Web Text)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1305. Min Act: -0.1700

Data Index: 3221242 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1305. Min Act: -0.1700

Data Index: 7161891 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.1305. Min Act: -0.1700

Data Index: 5141645 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.0680. Min Act: -0.1700

Data Index: 3017128 (Open Web Text)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 11.0680. Min Range: -11.0680

Max Act: 10.0680. Min Act: -0.1700

Data Index: 5740718 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #19