< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 6 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.8686. Min Act: -0.1700

Data Index: 8528621 (Open Web Text)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.7436. Min Act: -0.1700

Data Index: 886984 (Open Web Text)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.2436. Min Act: -0.1700

Data Index: 6336745 (Open Web Text)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.1186. Min Act: -0.1699

Data Index: 463568 (Open Web Text)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.3686. Min Act: -0.1699

Data Index: 1516813 (Open Web Text)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.0561. Min Act: -0.1700

Data Index: 5517086 (Open Web Text)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.1186. Min Act: -0.1700

Data Index: 2160540 (Open Web Text)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.1186. Min Act: -0.1700

Data Index: 1164258 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.0561. Min Act: -0.1700

Data Index: 970815 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.0561. Min Act: -0.1696

Data Index: 3438096 (Open Web Text)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.0561. Min Act: -0.1700

Data Index: 6449779 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 16.8686. Min Range: -16.8686

Max Act: 16.0561. Min Act: -0.1700

Data Index: 4734705 (Open Web Text)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9311. Min Act: -0.1700

Data Index: 4911100 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9936. Min Act: -0.1700

Data Index: 7630136 (Open Web Text)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9311. Min Act: -0.1700

Data Index: 8230417 (Open Web Text)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9311. Min Act: -0.1700

Data Index: 7206951 (Open Web Text)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9311. Min Act: -0.1700

Data Index: 142488 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9311. Min Act: -0.1700

Data Index: 894561 (Open Web Text)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.8686. Min Act: -0.1700

Data Index: 7656628 (Open Web Text)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 16.8686. Min Range: -16.8686

Max Act: 15.9311. Min Act: -0.1698

Data Index: 5226414 (Open Web Text)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #19