< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1601 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: 2.7721. Min Range: -2.7721

Max Act: 2.7683. Min Act: -0.1700

Data Index: 5563128 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.7721. Min Act: -0.1700

Data Index: 4754589 (Open Web Text)

Max Activating Token Index: 1000

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.7070. Min Act: -0.1700

Data Index: 5653981 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6897. Min Act: -0.1700

Data Index: 321596 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6792. Min Act: -0.1700

Data Index: 59682 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6544. Min Act: -0.1700

Data Index: 7883752 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6484. Min Act: -0.1700

Data Index: 1658363 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6396. Min Act: -0.1700

Data Index: 2261363 (Open Web Text)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6453. Min Act: -0.1700

Data Index: 6617666 (Open Web Text)

Max Activating Token Index: 197

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6253. Min Act: -0.1700

Data Index: 6181652 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6344. Min Act: -0.1700

Data Index: 5271297 (Open Web Text)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6208. Min Act: -0.1700

Data Index: 2078117 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6287. Min Act: -0.1700

Data Index: 1315321 (Open Web Text)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6217. Min Act: -0.1700

Data Index: 4903032 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6131. Min Act: -0.1700

Data Index: 2603655 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.6186. Min Act: -0.1700

Data Index: 4613009 (Open Web Text)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.5973. Min Act: -0.1700

Data Index: 3653842 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.5990. Min Act: -0.1700

Data Index: 5248861 (Open Web Text)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.5964. Min Act: -0.1700

Data Index: 5582884 (Open Web Text)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7721. Min Range: -2.7721

Max Act: 2.5919. Min Act: -0.1700

Data Index: 6116645 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #19