< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 562 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: 4.5597. Min Range: -4.5597

Max Act: 4.5597. Min Act: -0.1700

Data Index: 3306671 (Open Web Text)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.3872. Min Act: -0.1700

Data Index: 4878150 (Open Web Text)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.3348. Min Act: -0.1700

Data Index: 2679882 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.2984. Min Act: -0.1700

Data Index: 5488636 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.2914. Min Act: -0.1700

Data Index: 4956896 (Open Web Text)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.2105. Min Act: -0.1700

Data Index: 7988392 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.2103. Min Act: -0.1700

Data Index: 6962516 (Open Web Text)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1585. Min Act: -0.1700

Data Index: 1738268 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1983. Min Act: -0.1700

Data Index: 1716056 (Open Web Text)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1766. Min Act: -0.1700

Data Index: 3441469 (Open Web Text)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1607. Min Act: -0.1700

Data Index: 1208310 (Open Web Text)

Max Activating Token Index: 358

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1514. Min Act: -0.1700

Data Index: 992433 (Open Web Text)

Max Activating Token Index: 211

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1281. Min Act: -0.1700

Data Index: 7096028 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1222. Min Act: -0.1700

Data Index: 1080237 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1414. Min Act: -0.1700

Data Index: 2494431 (Open Web Text)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1363. Min Act: -0.1700

Data Index: 7226070 (Open Web Text)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1353. Min Act: -0.1700

Data Index: 4911082 (Open Web Text)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1503. Min Act: -0.1700

Data Index: 5039808 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1629. Min Act: -0.1700

Data Index: 5052143 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.5597. Min Range: -4.5597

Max Act: 4.1344. Min Act: -0.1700

Data Index: 5083607 (Open Web Text)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #19