< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1575 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: 2.9610. Min Range: -2.9610

Max Act: 2.9610. Min Act: -0.1700

Data Index: 4027753 (Open Web Text)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.9204. Min Act: -0.1700

Data Index: 7862825 (Open Web Text)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.9204. Min Act: -0.1700

Data Index: 4846255 (Open Web Text)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8860. Min Act: -0.1700

Data Index: 6101768 (Open Web Text)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.9058. Min Act: -0.1700

Data Index: 1465585 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8430. Min Act: -0.1700

Data Index: 2922335 (Open Web Text)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8505. Min Act: -0.1700

Data Index: 281385 (Open Web Text)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8621. Min Act: -0.1700

Data Index: 6310621 (Open Web Text)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8292. Min Act: -0.1700

Data Index: 5379115 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8585. Min Act: -0.1700

Data Index: 8231168 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8340. Min Act: -0.1700

Data Index: 2254253 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8468. Min Act: -0.1700

Data Index: 7892183 (Open Web Text)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8255. Min Act: -0.1700

Data Index: 8299296 (Open Web Text)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8177. Min Act: -0.1700

Data Index: 8560898 (Open Web Text)

Max Activating Token Index: 981

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8259. Min Act: -0.1700

Data Index: 6818721 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.7967. Min Act: -0.1700

Data Index: 801388 (Open Web Text)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.7741. Min Act: -0.1700

Data Index: 154536 (Open Web Text)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.7728. Min Act: -0.1700

Data Index: 5569833 (Open Web Text)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.7795. Min Act: -0.1700

Data Index: 5232646 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9610. Min Range: -2.9610

Max Act: 2.8122. Min Act: -0.1700

Data Index: 6343150 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #19