< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2751 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: 2.7543. Min Range: -2.7543

Max Act: 2.7543. Min Act: -0.1700

Data Index: 703157 (Open Web Text)

Max Activating Token Index: 670

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.7368. Min Act: -0.1700

Data Index: 1866725 (Open Web Text)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.7391. Min Act: -0.1700

Data Index: 1844329 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6814. Min Act: -0.1700

Data Index: 7664104 (Open Web Text)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6449. Min Act: -0.1700

Data Index: 3698227 (Open Web Text)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6506. Min Act: -0.1700

Data Index: 5277322 (Open Web Text)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6330. Min Act: -0.1700

Data Index: 8367130 (Open Web Text)

Max Activating Token Index: 980

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6147. Min Act: -0.1700

Data Index: 1726518 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6244. Min Act: -0.1700

Data Index: 2765783 (Open Web Text)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6171. Min Act: -0.1700

Data Index: 711937 (Open Web Text)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6109. Min Act: -0.1700

Data Index: 6250349 (Open Web Text)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5972. Min Act: -0.1700

Data Index: 3263113 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6059. Min Act: -0.1700

Data Index: 8091846 (Open Web Text)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5935. Min Act: -0.1700

Data Index: 4791506 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5996. Min Act: -0.1700

Data Index: 8525665 (Open Web Text)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.6089. Min Act: -0.1700

Data Index: 7454480 (Open Web Text)

Max Activating Token Index: 375

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5871. Min Act: -0.1700

Data Index: 8214534 (Open Web Text)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5756. Min Act: -0.1700

Data Index: 5598481 (Open Web Text)

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5816. Min Act: -0.1700

Data Index: 648414 (Open Web Text)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.7543. Min Range: -2.7543

Max Act: 2.5913. Min Act: -0.1700

Data Index: 5192493 (Open Web Text)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #19