< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1413 in Layer 5

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: 2.0642. Min Range: -2.0642

Max Act: 2.0642. Min Act: -0.1700

Data Index: 3607453 (Open Web Text)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9833. Min Act: -0.1700

Data Index: 3455153 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9696. Min Act: -0.1700

Data Index: 2845929 (Open Web Text)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9400. Min Act: -0.1700

Data Index: 2987606 (Open Web Text)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9544. Min Act: -0.1700

Data Index: 2935369 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9307. Min Act: -0.1700

Data Index: 6011329 (Open Web Text)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9206. Min Act: -0.1700

Data Index: 2596685 (Open Web Text)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9130. Min Act: -0.1700

Data Index: 7856339 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8915. Min Act: -0.1700

Data Index: 3326361 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8894. Min Act: -0.1700

Data Index: 835032 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8834. Min Act: -0.1700

Data Index: 1725466 (Open Web Text)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.9037. Min Act: -0.1700

Data Index: 4284009 (Open Web Text)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8860. Min Act: -0.1700

Data Index: 5390192 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8708. Min Act: -0.1700

Data Index: 6781285 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8724. Min Act: -0.1700

Data Index: 6900744 (Open Web Text)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8769. Min Act: -0.1700

Data Index: 5858655 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8736. Min Act: -0.1700

Data Index: 2147370 (Open Web Text)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8640. Min Act: -0.1700

Data Index: 7359006 (Open Web Text)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8616. Min Act: -0.1700

Data Index: 4621727 (Open Web Text)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0642. Min Range: -2.0642

Max Act: 1.8537. Min Act: -0.1700

Data Index: 3455152 (Open Web Text)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #19