< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1050 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: 2.9278. Min Range: -2.9278

Max Act: 2.9278. Min Act: -0.1700

Data Index: 3666066 (Open Web Text)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.9118. Min Act: -0.1700

Data Index: 2121274 (Open Web Text)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.8657. Min Act: -0.1700

Data Index: 7435743 (Open Web Text)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.8357. Min Act: -0.1700

Data Index: 2356507 (Open Web Text)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.8066. Min Act: -0.1700

Data Index: 5601637 (Open Web Text)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.8191. Min Act: -0.1700

Data Index: 669604 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7884. Min Act: -0.1700

Data Index: 1005250 (Open Web Text)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7986. Min Act: -0.1700

Data Index: 8444447 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.8110. Min Act: -0.1700

Data Index: 2686008 (Open Web Text)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7887. Min Act: -0.1700

Data Index: 5400930 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7913. Min Act: -0.1700

Data Index: 5539512 (Open Web Text)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7890. Min Act: -0.1700

Data Index: 5763159 (Open Web Text)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7694. Min Act: -0.1700

Data Index: 5385630 (Open Web Text)

Max Activating Token Index: 822

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7453. Min Act: -0.1700

Data Index: 5770827 (Open Web Text)

Max Activating Token Index: 890

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7651. Min Act: -0.1700

Data Index: 3544771 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7580. Min Act: -0.1700

Data Index: 1578482 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7465. Min Act: -0.1700

Data Index: 7783945 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7614. Min Act: -0.1700

Data Index: 5192455 (Open Web Text)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7594. Min Act: -0.1700

Data Index: 4564183 (Open Web Text)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9278. Min Range: -2.9278

Max Act: 2.7197. Min Act: -0.1700

Data Index: 4407526 (Open Web Text)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #19