< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2792 in Layer 5

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: 2.6841. Min Range: -2.6841

Max Act: 2.6602. Min Act: -0.1700

Data Index: 3928995 (Open Web Text)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.6841. Min Act: -0.1700

Data Index: 6820055 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.6550. Min Act: -0.1700

Data Index: 314809 (Open Web Text)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.6335. Min Act: -0.1700

Data Index: 6163401 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.6276. Min Act: -0.1700

Data Index: 1504142 (Open Web Text)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.6147. Min Act: -0.1700

Data Index: 1678447 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.6058. Min Act: -0.1700

Data Index: 4236375 (Open Web Text)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5917. Min Act: -0.1700

Data Index: 2915998 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5827. Min Act: -0.1700

Data Index: 429607 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5931. Min Act: -0.1700

Data Index: 5377624 (Open Web Text)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5802. Min Act: -0.1700

Data Index: 6740303 (Open Web Text)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5624. Min Act: -0.1700

Data Index: 2119240 (Open Web Text)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5473. Min Act: -0.1700

Data Index: 5721335 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5442. Min Act: -0.1700

Data Index: 6225018 (Open Web Text)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5206. Min Act: -0.1700

Data Index: 5345102 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5359. Min Act: -0.1700

Data Index: 2689263 (Open Web Text)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5360. Min Act: -0.1700

Data Index: 6946423 (Open Web Text)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5219. Min Act: -0.1700

Data Index: 7775798 (Open Web Text)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5239. Min Act: -0.1700

Data Index: 5705353 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6841. Min Range: -2.6841

Max Act: 2.5068. Min Act: -0.1700

Data Index: 5390172 (Open Web Text)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #19