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

Dataset: Open Web Text

Neuron 2649 in Layer 5

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: 5.2940. Min Range: -5.2940

Max Act: 5.2940. Min Act: -0.1700

Data Index: 7970182 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.1579. Min Act: -0.1700

Data Index: 1792771 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.1314. Min Act: -0.1700

Data Index: 8238566 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0815. Min Act: -0.1700

Data Index: 741850 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0660. Min Act: -0.1700

Data Index: 2937906 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0272. Min Act: -0.1700

Data Index: 6647117 (Open Web Text)

Max Activating Token Index: 549

Text #6

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0395. Min Act: -0.1700

Data Index: 6964724 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0455. Min Act: -0.1700

Data Index: 7075014 (Open Web Text)

Max Activating Token Index: 941

Text #8

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0254. Min Act: -0.1700

Data Index: 8098941 (Open Web Text)

Max Activating Token Index: 648

Text #9

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0559. Min Act: -0.1700

Data Index: 1226638 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0498. Min Act: -0.1700

Data Index: 4820739 (Open Web Text)

Max Activating Token Index: 31

Text #11

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0393. Min Act: -0.1700

Data Index: 5298315 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0293. Min Act: -0.1700

Data Index: 5636494 (Open Web Text)

Max Activating Token Index: 519

Text #13

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9907. Min Act: -0.1700

Data Index: 5375512 (Open Web Text)

Max Activating Token Index: 290

Text #14

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9917. Min Act: -0.1700

Data Index: 7420882 (Open Web Text)

Max Activating Token Index: 768

Text #15

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9809. Min Act: -0.1700

Data Index: 3968612 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0196. Min Act: -0.1700

Data Index: 7194820 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0108. Min Act: -0.1700

Data Index: 2662534 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 5.2940. Min Range: -5.2940

Max Act: 5.0091. Min Act: -0.1700

Data Index: 3919795 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 5.2940. Min Range: -5.2940

Max Act: 4.9958. Min Act: -0.1700

Data Index: 3802695 (Open Web Text)

Max Activating Token Index: 565