< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 4023 in Layer 17

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.0827. Min Range: -4.0827

Max Act: 4.0827. Min Act: -0.1700

Data Index: 5154269 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9420. Min Act: -0.1700

Data Index: 4071197 (Open Web Text)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9264. Min Act: -0.1700

Data Index: 2982802 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9264. Min Act: -0.1700

Data Index: 3743477 (Open Web Text)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9107. Min Act: -0.1700

Data Index: 3012580 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.9107. Min Act: -0.1700

Data Index: 2566580 (Open Web Text)

Max Activating Token Index: 939

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1777591 (Open Web Text)

Max Activating Token Index: 791

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8795. Min Act: -0.1700

Data Index: 1578958 (Open Web Text)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8795. Min Act: -0.1700

Data Index: 4839155 (Open Web Text)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8795. Min Act: -0.1700

Data Index: 4075019 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8482. Min Act: -0.1700

Data Index: 7187106 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8795. Min Act: -0.1700

Data Index: 8472775 (Open Web Text)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8638. Min Act: -0.1700

Data Index: 4622073 (Open Web Text)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8482. Min Act: -0.1700

Data Index: 4367995 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8169. Min Act: -0.1700

Data Index: 6061204 (Open Web Text)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8169. Min Act: -0.1700

Data Index: 5837001 (Open Web Text)

Max Activating Token Index: 374

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.8169. Min Act: -0.1700

Data Index: 6726176 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.7856. Min Act: -0.1700

Data Index: 1411421 (Open Web Text)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.7856. Min Act: -0.1700

Data Index: 3579314 (Open Web Text)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0827. Min Range: -4.0827

Max Act: 3.7856. Min Act: -0.1700

Data Index: 6111543 (Open Web Text)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #19