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

Dataset: Open Web Text

Neuron 1740 in Layer 3

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: 4.0163. Min Range: -4.0163

Max Act: 4.0163. Min Act: -0.1700

Data Index: 6389090 (Open Web Text)

Max Activating Token Index: 746

Text #1

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8890. Min Act: -0.1700

Data Index: 4467599 (Open Web Text)

Max Activating Token Index: 932

Text #2

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8801. Min Act: -0.1700

Data Index: 7196264 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8556. Min Act: -0.1700

Data Index: 6004878 (Open Web Text)

Max Activating Token Index: 303

Text #4

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8737. Min Act: -0.1700

Data Index: 4652444 (Open Web Text)

Max Activating Token Index: 451

Text #5

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8309. Min Act: -0.1700

Data Index: 1216280 (Open Web Text)

Max Activating Token Index: 233

Text #6

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8386. Min Act: -0.1700

Data Index: 354582 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8385. Min Act: -0.1700

Data Index: 7611572 (Open Web Text)

Max Activating Token Index: 539

Text #8

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8194. Min Act: -0.1700

Data Index: 4224669 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8102. Min Act: -0.1700

Data Index: 3917883 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7832. Min Act: -0.1700

Data Index: 2490586 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8013. Min Act: -0.1700

Data Index: 413141 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.8038. Min Act: -0.1700

Data Index: 7129444 (Open Web Text)

Max Activating Token Index: 703

Text #13

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7685. Min Act: -0.1700

Data Index: 7436554 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7801. Min Act: -0.1700

Data Index: 41815 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7550. Min Act: -0.1700

Data Index: 7643750 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7813. Min Act: -0.1700

Data Index: 8152159 (Open Web Text)

Max Activating Token Index: 546

Text #17

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7472. Min Act: -0.1700

Data Index: 8751413 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7741. Min Act: -0.1700

Data Index: 3707166 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 4.0163. Min Range: -4.0163

Max Act: 3.7608. Min Act: -0.1700

Data Index: 3610936 (Open Web Text)

Max Activating Token Index: 4