< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1202 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: 2.2013. Min Range: -2.2013

Max Act: 2.2013. Min Act: -0.1700

Data Index: 5469558 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1570. Min Act: -0.1700

Data Index: 2775539 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1599. Min Act: -0.1700

Data Index: 5958009 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1486. Min Act: -0.1700

Data Index: 262633 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1222. Min Act: -0.1700

Data Index: 5107153 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1147. Min Act: -0.1700

Data Index: 2197893 (Open Web Text)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1026. Min Act: -0.1700

Data Index: 2491776 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.1114. Min Act: -0.1700

Data Index: 4632040 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0891. Min Act: -0.1700

Data Index: 6061066 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0880. Min Act: -0.1700

Data Index: 8610179 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0848. Min Act: -0.1700

Data Index: 8296476 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0836. Min Act: -0.1700

Data Index: 3803417 (Open Web Text)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0879. Min Act: -0.1700

Data Index: 7062095 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0961. Min Act: -0.1700

Data Index: 1812292 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0826. Min Act: -0.1700

Data Index: 3798233 (Open Web Text)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0450. Min Act: -0.1700

Data Index: 2043563 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0550. Min Act: -0.1700

Data Index: 5190796 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0528. Min Act: -0.1700

Data Index: 7139015 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0460. Min Act: -0.1700

Data Index: 2073392 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2013. Min Range: -2.2013

Max Act: 2.0424. Min Act: -0.1700

Data Index: 3407109 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19