< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2417 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: 4.2820. Min Range: -4.2820

Max Act: 4.2820. Min Act: -0.1700

Data Index: 8249589 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.2719. Min Act: -0.1700

Data Index: 5501717 (Open Web Text)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.2023. Min Act: -0.1700

Data Index: 6505485 (Open Web Text)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.2064. Min Act: -0.1700

Data Index: 3835892 (Open Web Text)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1745. Min Act: -0.1700

Data Index: 2833949 (Open Web Text)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.2033. Min Act: -0.1700

Data Index: 158082 (Open Web Text)

Max Activating Token Index: 627

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.2038. Min Act: -0.1700

Data Index: 7106883 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1699. Min Act: -0.1700

Data Index: 4319283 (Open Web Text)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1332. Min Act: -0.1700

Data Index: 8069098 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1541. Min Act: -0.1700

Data Index: 6591331 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1552. Min Act: -0.1700

Data Index: 6356272 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1442. Min Act: -0.1700

Data Index: 2658423 (Open Web Text)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1586. Min Act: -0.1700

Data Index: 4351793 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1340. Min Act: -0.1700

Data Index: 2576418 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1302. Min Act: -0.1700

Data Index: 1341960 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1416. Min Act: -0.1700

Data Index: 3530311 (Open Web Text)

Max Activating Token Index: 730

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1126. Min Act: -0.1700

Data Index: 5926959 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1132. Min Act: -0.1700

Data Index: 8563650 (Open Web Text)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1220. Min Act: -0.1700

Data Index: 2206492 (Open Web Text)

Max Activating Token Index: 656

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.2820. Min Range: -4.2820

Max Act: 4.1100. Min Act: -0.1700

Data Index: 7030734 (Open Web Text)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #19