< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1443 in Layer 0

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: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 5483570 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 5642195 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 8553075 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 8230934 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 3199789 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 4447250 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 2565423 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 7881535 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8283. Min Act: -0.1700

Data Index: 834464 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 2386157 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8335. Min Act: -0.1700

Data Index: 2208025 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8111. Min Act: -0.1700

Data Index: 1317128 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8111. Min Act: -0.1700

Data Index: 915021 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8111. Min Act: -0.1700

Data Index: 2570055 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8013. Min Act: -0.1700

Data Index: 661020 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8069. Min Act: -0.1700

Data Index: 2940466 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.8111. Min Act: -0.1700

Data Index: 8558806 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.7845. Min Act: -0.1700

Data Index: 7614616 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.7780. Min Act: -0.1700

Data Index: 8697380 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8335. Min Range: -2.8335

Max Act: 2.7922. Min Act: -0.1700

Data Index: 4965410 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #19