< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2188 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: 4.5624. Min Range: -4.5624

Max Act: 4.5624. Min Act: -0.1700

Data Index: 173747 (Open Web Text)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.5227. Min Act: -0.1700

Data Index: 4252475 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4601. Min Act: -0.1700

Data Index: 5983831 (Open Web Text)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4390. Min Act: -0.1700

Data Index: 3497659 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4167. Min Act: -0.1700

Data Index: 1759735 (Open Web Text)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4180. Min Act: -0.1700

Data Index: 3144214 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4274. Min Act: -0.1700

Data Index: 7381949 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4151. Min Act: -0.1700

Data Index: 1531418 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4316. Min Act: -0.1700

Data Index: 5170903 (Open Web Text)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4494. Min Act: -0.1700

Data Index: 4868400 (Open Web Text)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3869. Min Act: -0.1700

Data Index: 1599262 (Open Web Text)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4020. Min Act: -0.1700

Data Index: 5683606 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3780. Min Act: -0.1700

Data Index: 4065979 (Open Web Text)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4122. Min Act: -0.1700

Data Index: 7843918 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3926. Min Act: -0.1700

Data Index: 6060686 (Open Web Text)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.4040. Min Act: -0.1700

Data Index: 6005451 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3600. Min Act: -0.1700

Data Index: 659806 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3838. Min Act: -0.1700

Data Index: 2095401 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3491. Min Act: -0.1700

Data Index: 3053916 (Open Web Text)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.5624. Min Range: -4.5624

Max Act: 4.3862. Min Act: -0.1700

Data Index: 3093499 (Open Web Text)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #19