< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1004 in Layer 4

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: 2.6669. Min Range: -2.6669

Max Act: 2.6669. Min Act: -0.1700

Data Index: 541784 (Open Web Text)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.6298. Min Act: -0.1700

Data Index: 4741514 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.6430. Min Act: -0.1700

Data Index: 7439365 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.6236. Min Act: -0.1700

Data Index: 1915500 (Open Web Text)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5916. Min Act: -0.1700

Data Index: 3525342 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5950. Min Act: -0.1700

Data Index: 5777081 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5897. Min Act: -0.1700

Data Index: 5275917 (Open Web Text)

Max Activating Token Index: 764

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5799. Min Act: -0.1700

Data Index: 6204377 (Open Web Text)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5497. Min Act: -0.1700

Data Index: 515037 (Open Web Text)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5876. Min Act: -0.1700

Data Index: 1289267 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5876. Min Act: -0.1700

Data Index: 7505972 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.6042. Min Act: -0.1700

Data Index: 8498023 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5876. Min Act: -0.1700

Data Index: 5086099 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5876. Min Act: -0.1700

Data Index: 3259679 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5876. Min Act: -0.1700

Data Index: 5167472 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5684. Min Act: -0.1700

Data Index: 6273613 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5771. Min Act: -0.1700

Data Index: 6144197 (Open Web Text)

Max Activating Token Index: 114

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5855. Min Act: -0.1700

Data Index: 6937327 (Open Web Text)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5635. Min Act: -0.1700

Data Index: 627616 (Open Web Text)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6669. Min Range: -2.6669

Max Act: 2.5611. Min Act: -0.1700

Data Index: 5000078 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #19