< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4928. Min Act: -0.1700

Data Index: 6892598 (Open Web Text)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4838. Min Act: -0.1700

Data Index: 2676737 (Open Web Text)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4594. Min Act: -0.1700

Data Index: 7382030 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4837. Min Act: -0.1700

Data Index: 8426442 (Open Web Text)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4255. Min Act: -0.1700

Data Index: 199347 (Open Web Text)

Max Activating Token Index: 420

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4128. Min Act: -0.1700

Data Index: 74967 (Open Web Text)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4163. Min Act: -0.1700

Data Index: 5017841 (Open Web Text)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3871. Min Act: -0.1700

Data Index: 7102249 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4042. Min Act: -0.1700

Data Index: 278264 (Open Web Text)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4268. Min Act: -0.1700

Data Index: 516651 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.4142. Min Act: -0.1700

Data Index: 3873074 (Open Web Text)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3889. Min Act: -0.1700

Data Index: 8717072 (Open Web Text)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3856. Min Act: -0.1700

Data Index: 1480778 (Open Web Text)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3762. Min Act: -0.1700

Data Index: 8213946 (Open Web Text)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3609. Min Act: -0.1700

Data Index: 4102755 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3868. Min Act: -0.1700

Data Index: 7434303 (Open Web Text)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3600. Min Act: -0.1700

Data Index: 3625777 (Open Web Text)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3561. Min Act: -0.1700

Data Index: 5035272 (Open Web Text)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3623. Min Act: -0.1700

Data Index: 7161118 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4928. Min Range: -2.4928

Max Act: 2.3673. Min Act: -0.1700

Data Index: 6751749 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #19