< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 186 in Layer 1

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: 2.0267. Min Range: -2.0267

Max Act: 2.0267. Min Act: -0.1700

Data Index: 1719104 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0253. Min Act: -0.1700

Data Index: 5128049 (Open Web Text)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0202. Min Act: -0.1700

Data Index: 4282533 (Open Web Text)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0173. Min Act: -0.1700

Data Index: 2402195 (Open Web Text)

Max Activating Token Index: 515

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0113. Min Act: -0.1700

Data Index: 2744638 (Open Web Text)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9986. Min Act: -0.1700

Data Index: 2785963 (Open Web Text)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0267. Min Range: -2.0267

Max Act: 2.0030. Min Act: -0.1700

Data Index: 4892756 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9999. Min Act: -0.1700

Data Index: 6969245 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9828. Min Act: -0.1700

Data Index: 2136479 (Open Web Text)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9824. Min Act: -0.1700

Data Index: 6010625 (Open Web Text)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9811. Min Act: -0.1700

Data Index: 870786 (Open Web Text)

Max Activating Token Index: 340

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9726. Min Act: -0.1700

Data Index: 7448035 (Open Web Text)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9613. Min Act: -0.1700

Data Index: 4331259 (Open Web Text)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9730. Min Act: -0.1700

Data Index: 4243385 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9677. Min Act: -0.1700

Data Index: 7494831 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9547. Min Act: -0.1700

Data Index: 3569137 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9575. Min Act: -0.1700

Data Index: 7205686 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9503. Min Act: -0.1700

Data Index: 7260978 (Open Web Text)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9630. Min Act: -0.1700

Data Index: 2933776 (Open Web Text)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0267. Min Range: -2.0267

Max Act: 1.9495. Min Act: -0.1700

Data Index: 3111062 (Open Web Text)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #19