< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 8 in Layer 47

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.8923. Min Act: -0.1700

Data Index: 2787391 (Open Web Text)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.6423. Min Act: -0.1700

Data Index: 1526049 (Open Web Text)

Max Activating Token Index: 953

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.4548. Min Act: -0.1700

Data Index: 721955 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.4548. Min Act: -0.1700

Data Index: 2277632 (Open Web Text)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2673. Min Act: -0.1700

Data Index: 721949 (Open Web Text)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2673. Min Act: -0.1700

Data Index: 2277638 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2048. Min Act: -0.1700

Data Index: 1060593 (Open Web Text)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2673. Min Act: -0.1700

Data Index: 1031537 (Open Web Text)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2048. Min Act: -0.1700

Data Index: 2582349 (Open Web Text)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2048. Min Act: -0.1700

Data Index: 721944 (Open Web Text)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2673. Min Act: -0.1700

Data Index: 2277640 (Open Web Text)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.1423. Min Act: -0.1700

Data Index: 6327150 (Open Web Text)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.1423. Min Act: -0.1700

Data Index: 5766901 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.2048. Min Act: -0.1700

Data Index: 6594278 (Open Web Text)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.0798. Min Act: -0.1700

Data Index: 7442791 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.1423. Min Act: -0.1700

Data Index: 8686236 (Open Web Text)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.0798. Min Act: -0.1700

Data Index: 2925269 (Open Web Text)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.0798. Min Act: -0.1700

Data Index: 6702535 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.1423. Min Act: -0.1700

Data Index: 1446525 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.8923. Min Range: -10.8923

Max Act: 10.0798. Min Act: -0.1700

Data Index: 7960667 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #19