< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2581 in Layer 6

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: 9.3500. Min Range: -9.3500

Max Act: 9.3500. Min Act: -0.1700

Data Index: 2253762 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.3027. Min Act: -0.1700

Data Index: 6601095 (Open Web Text)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.2631. Min Act: -0.1700

Data Index: 3685235 (Open Web Text)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.2891. Min Act: -0.1700

Data Index: 4901106 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.2059. Min Act: -0.1700

Data Index: 6311405 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.1921. Min Act: -0.1700

Data Index: 792864 (Open Web Text)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0304. Min Act: -0.1700

Data Index: 4218523 (Open Web Text)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0560. Min Act: -0.1700

Data Index: 5688027 (Open Web Text)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0484. Min Act: -0.1700

Data Index: 4647137 (Open Web Text)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.1111. Min Act: -0.1700

Data Index: 7373537 (Open Web Text)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0234. Min Act: -0.1700

Data Index: 1800839 (Open Web Text)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0410. Min Act: -0.1700

Data Index: 4840702 (Open Web Text)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0463. Min Act: -0.1700

Data Index: 8087897 (Open Web Text)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 9.3500. Min Range: -9.3500

Max Act: 8.9897. Min Act: -0.1700

Data Index: 1761349 (Open Web Text)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 9.3500. Min Range: -9.3500

Max Act: 9.0247. Min Act: -0.1700

Data Index: 7248513 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 9.3500. Min Range: -9.3500

Max Act: 8.8970. Min Act: -0.1700

Data Index: 1422854 (Open Web Text)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 9.3500. Min Range: -9.3500

Max Act: 8.9020. Min Act: -0.1700

Data Index: 6747181 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 9.3500. Min Range: -9.3500

Max Act: 8.8478. Min Act: -0.1700

Data Index: 2458306 (Open Web Text)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 9.3500. Min Range: -9.3500

Max Act: 8.8763. Min Act: -0.1700

Data Index: 5578660 (Open Web Text)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 9.3500. Min Range: -9.3500

Max Act: 8.8136. Min Act: -0.1700

Data Index: 6836268 (Open Web Text)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #19