< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2575 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.5165. Min Act: -0.1700

Data Index: 5959562 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.5165. Min Act: -0.1700

Data Index: 6910743 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.5084. Min Act: -0.1700

Data Index: 4610282 (Open Web Text)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.5050. Min Act: -0.1700

Data Index: 7620589 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.5050. Min Act: -0.1700

Data Index: 2308150 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.5050. Min Act: -0.1700

Data Index: 3706597 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3729. Min Act: -0.1700

Data Index: 5091494 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3644. Min Act: -0.1700

Data Index: 2370114 (Open Web Text)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3729. Min Act: -0.1700

Data Index: 3939666 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3729. Min Act: -0.1700

Data Index: 4400076 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3729. Min Act: -0.1700

Data Index: 644609 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3729. Min Act: -0.1700

Data Index: 2026855 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3729. Min Act: -0.1700

Data Index: 4378152 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3497. Min Act: -0.1700

Data Index: 2249794 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3299. Min Act: -0.1700

Data Index: 3795130 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3241. Min Act: -0.1700

Data Index: 3363487 (Open Web Text)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3285. Min Act: -0.1700

Data Index: 2791480 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3098. Min Act: -0.1700

Data Index: 8078408 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.3087. Min Act: -0.1700

Data Index: 5914336 (Open Web Text)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5165. Min Range: -2.5165

Max Act: 2.2855. Min Act: -0.1700

Data Index: 3232452 (Open Web Text)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #19