< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1625 in Layer 3

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: 2.0090. Min Range: -2.0090

Max Act: 2.0090. Min Act: -0.1700

Data Index: 1500712 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.9650. Min Act: -0.1700

Data Index: 8382459 (Open Web Text)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.9452. Min Act: -0.1700

Data Index: 2282197 (Open Web Text)

Max Activating Token Index: 789

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.9254. Min Act: -0.1700

Data Index: 5436297 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.9053. Min Act: -0.1700

Data Index: 459591 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.9112. Min Act: -0.1700

Data Index: 6230699 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.9132. Min Act: -0.1700

Data Index: 551125 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8920. Min Act: -0.1700

Data Index: 2830120 (Open Web Text)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8858. Min Act: -0.1700

Data Index: 4495044 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8748. Min Act: -0.1700

Data Index: 7773416 (Open Web Text)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8923. Min Act: -0.1700

Data Index: 5436298 (Open Web Text)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8679. Min Act: -0.1700

Data Index: 5681971 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8744. Min Act: -0.1700

Data Index: 558084 (Open Web Text)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8747. Min Act: -0.1700

Data Index: 5444631 (Open Web Text)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8797. Min Act: -0.1700

Data Index: 4258431 (Open Web Text)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8606. Min Act: -0.1700

Data Index: 5433704 (Open Web Text)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8615. Min Act: -0.1700

Data Index: 1828428 (Open Web Text)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8762. Min Act: -0.1700

Data Index: 5643330 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8427. Min Act: -0.1700

Data Index: 2933145 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0090. Min Range: -2.0090

Max Act: 1.8569. Min Act: -0.1700

Data Index: 3647399 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #19