< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2017 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: 3.4166. Min Range: -3.4166

Max Act: 3.4166. Min Act: -0.1700

Data Index: 2682385 (Open Web Text)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 3.4166. Min Range: -3.4166

Max Act: 3.1881. Min Act: -0.1700

Data Index: 1182690 (Open Web Text)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 3.4166. Min Range: -3.4166

Max Act: 3.0601. Min Act: -0.1700

Data Index: 29767 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 3.4166. Min Range: -3.4166

Max Act: 3.0373. Min Act: -0.1700

Data Index: 5214666 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 3.4166. Min Range: -3.4166

Max Act: 3.0170. Min Act: -0.1700

Data Index: 7036248 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9930. Min Act: -0.1700

Data Index: 8629031 (Open Web Text)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9791. Min Act: -0.1700

Data Index: 7578595 (Open Web Text)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9705. Min Act: -0.1700

Data Index: 4694923 (Open Web Text)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9914. Min Act: -0.1700

Data Index: 740893 (Open Web Text)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9988. Min Act: -0.1700

Data Index: 6534576 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9766. Min Act: -0.1700

Data Index: 3685225 (Open Web Text)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9493. Min Act: -0.1700

Data Index: 5511506 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9446. Min Act: -0.1700

Data Index: 4209976 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9676. Min Act: -0.1700

Data Index: 4073204 (Open Web Text)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9582. Min Act: -0.1700

Data Index: 1767241 (Open Web Text)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9466. Min Act: -0.1700

Data Index: 7267012 (Open Web Text)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9364. Min Act: -0.1700

Data Index: 7871550 (Open Web Text)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9175. Min Act: -0.1700

Data Index: 7669222 (Open Web Text)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.9141. Min Act: -0.1700

Data Index: 4954738 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 3.4166. Min Range: -3.4166

Max Act: 2.8667. Min Act: -0.1700

Data Index: 2291918 (Open Web Text)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #19