< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2120 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: 1.2012. Min Range: -1.2012

Max Act: 1.2012. Min Act: -0.1700

Data Index: 3671032 (Open Web Text)

Max Activating Token Index: 631

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1849. Min Act: -0.1700

Data Index: 2545485 (Open Web Text)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1609. Min Act: -0.1700

Data Index: 6799546 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1608. Min Act: -0.1700

Data Index: 6067826 (Open Web Text)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1561. Min Act: -0.1699

Data Index: 3134327 (Open Web Text)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1402. Min Act: -0.1700

Data Index: 6213191 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1259. Min Act: -0.1700

Data Index: 3398133 (Open Web Text)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1128. Min Act: -0.1690

Data Index: 463735 (Open Web Text)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.1034. Min Act: -0.1700

Data Index: 7638 (Open Web Text)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0911. Min Act: -0.1698

Data Index: 3397589 (Open Web Text)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0915. Min Act: -0.1699

Data Index: 4462200 (Open Web Text)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0934. Min Act: -0.1700

Data Index: 8777014 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0955. Min Act: -0.1700

Data Index: 3891811 (Open Web Text)

Max Activating Token Index: 1011

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0936. Min Act: -0.1700

Data Index: 4981128 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0905. Min Act: -0.1700

Data Index: 4662581 (Open Web Text)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0804. Min Act: -0.1695

Data Index: 2166178 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0824. Min Act: -0.1699

Data Index: 3671035 (Open Web Text)

Max Activating Token Index: 576

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0814. Min Act: -0.1700

Data Index: 1541329 (Open Web Text)

Max Activating Token Index: 354

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0754. Min Act: -0.1700

Data Index: 1027704 (Open Web Text)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 1.2012. Min Range: -1.2012

Max Act: 1.0769. Min Act: -0.1700

Data Index: 6190249 (Open Web Text)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #19