< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2803 in Layer 3

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: 2.8429. Min Range: -2.8429

Max Act: 2.8429. Min Act: -0.1700

Data Index: 7616803 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.7298. Min Act: -0.1700

Data Index: 1313288 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.7298. Min Act: -0.1700

Data Index: 7669318 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6766. Min Act: -0.1700

Data Index: 4807414 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6766. Min Act: -0.1700

Data Index: 7321911 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6608. Min Act: -0.1700

Data Index: 5684612 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6432. Min Act: -0.1700

Data Index: 3665641 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6389. Min Act: -0.1700

Data Index: 2139256 (Open Web Text)

Max Activating Token Index: 43

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6463. Min Act: -0.1700

Data Index: 3745841 (Open Web Text)

Max Activating Token Index: 285

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6238. Min Act: -0.1700

Data Index: 1041618 (Open Web Text)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6363. Min Act: -0.1700

Data Index: 1901051 (Open Web Text)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.5864. Min Act: -0.1700

Data Index: 4969877 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6387. Min Act: -0.1700

Data Index: 4460443 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6343. Min Act: -0.1700

Data Index: 3862622 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6053. Min Act: -0.1700

Data Index: 7909991 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.5808. Min Act: -0.1700

Data Index: 5863786 (Open Web Text)

Max Activating Token Index: 648

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.5859. Min Act: -0.1700

Data Index: 4527244 (Open Web Text)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6160. Min Act: -0.1700

Data Index: 3306077 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.6109. Min Act: -0.1700

Data Index: 5857419 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8429. Min Range: -2.8429

Max Act: 2.5788. Min Act: -0.1700

Data Index: 7349597 (Open Web Text)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #19