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

Dataset: Open Web Text

Neuron 763 in Layer 6

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: 5.5337. Min Range: -5.5337

Max Act: 5.5337. Min Act: -0.1700

Data Index: 4039726 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.3967. Min Act: -0.1700

Data Index: 5529606 (Open Web Text)

Max Activating Token Index: 770

Text #2

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.3828. Min Act: -0.1700

Data Index: 6299122 (Open Web Text)

Max Activating Token Index: 699

Text #3

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.3510. Min Act: -0.1700

Data Index: 883918 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.3173. Min Act: -0.1700

Data Index: 6414568 (Open Web Text)

Max Activating Token Index: 205

Text #5

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2876. Min Act: -0.1700

Data Index: 2303987 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2683. Min Act: -0.1700

Data Index: 6427109 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2561. Min Act: -0.1700

Data Index: 8504082 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2081. Min Act: -0.1700

Data Index: 6957226 (Open Web Text)

Max Activating Token Index: 637

Text #9

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2029. Min Act: -0.1700

Data Index: 473707 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2314. Min Act: -0.1700

Data Index: 5836904 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2193. Min Act: -0.1700

Data Index: 1677487 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.1932. Min Act: -0.1700

Data Index: 6038347 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2218. Min Act: -0.1700

Data Index: 5022157 (Open Web Text)

Max Activating Token Index: 897

Text #14

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2045. Min Act: -0.1700

Data Index: 760393 (Open Web Text)

Max Activating Token Index: 171

Text #15

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.1619. Min Act: -0.1700

Data Index: 5629019 (Open Web Text)

Max Activating Token Index: 161

Text #16

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.1727. Min Act: -0.1700

Data Index: 4274326 (Open Web Text)

Max Activating Token Index: 566

Text #17

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.1576. Min Act: -0.1700

Data Index: 6949688 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.1803. Min Act: -0.1700

Data Index: 6538877 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 5.5337. Min Range: -5.5337

Max Act: 5.2220. Min Act: -0.1700

Data Index: 2032891 (Open Web Text)

Max Activating Token Index: 572