< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 513 in Layer 2

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: 2.1067. Min Range: -2.1067

Max Act: 2.1052. Min Act: -0.1700

Data Index: 8351736 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.1067. Min Act: -0.1700

Data Index: 6398190 (Open Web Text)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.0546. Min Act: -0.1700

Data Index: 676166 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.0468. Min Act: -0.1700

Data Index: 6589681 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.0352. Min Act: -0.1700

Data Index: 7364887 (Open Web Text)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.0116. Min Act: -0.1700

Data Index: 607350 (Open Web Text)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9838. Min Act: -0.1700

Data Index: 3433452 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9811. Min Act: -0.1700

Data Index: 4049694 (Open Web Text)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1067. Min Range: -2.1067

Max Act: 2.0044. Min Act: -0.1700

Data Index: 6355738 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9990. Min Act: -0.1700

Data Index: 1107493 (Open Web Text)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9842. Min Act: -0.1700

Data Index: 6153383 (Open Web Text)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9904. Min Act: -0.1700

Data Index: 7712401 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9540. Min Act: -0.1700

Data Index: 4019051 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9562. Min Act: -0.1700

Data Index: 6295137 (Open Web Text)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9597. Min Act: -0.1700

Data Index: 8161030 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9639. Min Act: -0.1700

Data Index: 3725458 (Open Web Text)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9879. Min Act: -0.1700

Data Index: 7087287 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9639. Min Act: -0.1700

Data Index: 4643013 (Open Web Text)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9574. Min Act: -0.1700

Data Index: 4828083 (Open Web Text)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1067. Min Range: -2.1067

Max Act: 1.9442. Min Act: -0.1700

Data Index: 46145 (Open Web Text)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #19