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

Dataset: Open Web Text

Neuron 270 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: 1.6538. Min Range: -1.6538

Max Act: 1.6538. Min Act: -0.1693

Data Index: 3645151 (Open Web Text)

Max Activating Token Index: 907

Text #1

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6403. Min Act: -0.1700

Data Index: 8794932 (Open Web Text)

Max Activating Token Index: 670

Text #2

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6426. Min Act: -0.1699

Data Index: 4844556 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6246. Min Act: -0.1700

Data Index: 7275566 (Open Web Text)

Max Activating Token Index: 810

Text #4

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6055. Min Act: -0.1700

Data Index: 7232072 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6050. Min Act: -0.1700

Data Index: 7730420 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6027. Min Act: -0.1700

Data Index: 3131513 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6058. Min Act: -0.1699

Data Index: 8255586 (Open Web Text)

Max Activating Token Index: 481

Text #8

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6024. Min Act: -0.1700

Data Index: 6245182 (Open Web Text)

Max Activating Token Index: 825

Text #9

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5977. Min Act: -0.1700

Data Index: 8256905 (Open Web Text)

Max Activating Token Index: 733

Text #10

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5932. Min Act: -0.1700

Data Index: 4944 (Open Web Text)

Max Activating Token Index: 790

Text #11

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5960. Min Act: -0.1700

Data Index: 1392877 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5940. Min Act: -0.1700

Data Index: 2169393 (Open Web Text)

Max Activating Token Index: 789

Text #13

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.6013. Min Act: -0.1697

Data Index: 1523171 (Open Web Text)

Max Activating Token Index: 536

Text #14

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5848. Min Act: -0.1700

Data Index: 887670 (Open Web Text)

Max Activating Token Index: 947

Text #15

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5827. Min Act: -0.1700

Data Index: 1646724 (Open Web Text)

Max Activating Token Index: 299

Text #16

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5999. Min Act: -0.1700

Data Index: 109577 (Open Web Text)

Max Activating Token Index: 996

Text #17

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5937. Min Act: -0.1700

Data Index: 3706527 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5931. Min Act: -0.1700

Data Index: 3103590 (Open Web Text)

Max Activating Token Index: 178

Text #19

Max Range: 1.6538. Min Range: -1.6538

Max Act: 1.5879. Min Act: -0.1700

Data Index: 6596261 (Open Web Text)

Max Activating Token Index: 969