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

Dataset: Open Web Text

Neuron 107 in Layer 4

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: 5.3008. Min Range: -5.3008

Max Act: 5.3008. Min Act: -0.1700

Data Index: 2895482 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.2564. Min Act: -0.1700

Data Index: 5572807 (Open Web Text)

Max Activating Token Index: 320

Text #2

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.2432. Min Act: -0.1700

Data Index: 377137 (Open Web Text)

Max Activating Token Index: 224

Text #3

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1754. Min Act: -0.1700

Data Index: 4836147 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1885. Min Act: -0.1700

Data Index: 6416736 (Open Web Text)

Max Activating Token Index: 634

Text #5

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1400. Min Act: -0.1700

Data Index: 6203870 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1821. Min Act: -0.1700

Data Index: 7586513 (Open Web Text)

Max Activating Token Index: 716

Text #7

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1252. Min Act: -0.1700

Data Index: 8013485 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1284. Min Act: -0.1700

Data Index: 4792703 (Open Web Text)

Max Activating Token Index: 805

Text #9

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.1522. Min Act: -0.1700

Data Index: 3919907 (Open Web Text)

Max Activating Token Index: 376

Text #10

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0640. Min Act: -0.1700

Data Index: 8263327 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0575. Min Act: -0.1700

Data Index: 744287 (Open Web Text)

Max Activating Token Index: 921

Text #12

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0656. Min Act: -0.1700

Data Index: 2448744 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0649. Min Act: -0.1698

Data Index: 7066207 (Open Web Text)

Max Activating Token Index: 328

Text #14

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0805. Min Act: -0.1700

Data Index: 7409547 (Open Web Text)

Max Activating Token Index: 869

Text #15

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0804. Min Act: -0.1700

Data Index: 6059660 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0474. Min Act: -0.1700

Data Index: 2198677 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0435. Min Act: -0.1700

Data Index: 3169049 (Open Web Text)

Max Activating Token Index: 502

Text #18

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0205. Min Act: -0.1700

Data Index: 4673831 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 5.3008. Min Range: -5.3008

Max Act: 5.0108. Min Act: -0.1700

Data Index: 8220987 (Open Web Text)

Max Activating Token Index: 124