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

Dataset: Open Web Text

Neuron 1261 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: 4.7736. Min Range: -4.7736

Max Act: 4.7736. Min Act: -0.1700

Data Index: 7970612 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.7303. Min Act: -0.1700

Data Index: 4415482 (Open Web Text)

Max Activating Token Index: 638

Text #2

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.7141. Min Act: -0.1700

Data Index: 6249097 (Open Web Text)

Max Activating Token Index: 314

Text #3

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.7142. Min Act: -0.1700

Data Index: 7165399 (Open Web Text)

Max Activating Token Index: 566

Text #4

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6968. Min Act: -0.1700

Data Index: 7191511 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.7033. Min Act: -0.1700

Data Index: 1676828 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.7112. Min Act: -0.1700

Data Index: 7783039 (Open Web Text)

Max Activating Token Index: 509

Text #7

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6463. Min Act: -0.1700

Data Index: 2289703 (Open Web Text)

Max Activating Token Index: 813

Text #8

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6723. Min Act: -0.1700

Data Index: 1606629 (Open Web Text)

Max Activating Token Index: 803

Text #9

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6782. Min Act: -0.1700

Data Index: 4926795 (Open Web Text)

Max Activating Token Index: 490

Text #10

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6670. Min Act: -0.1700

Data Index: 1495190 (Open Web Text)

Max Activating Token Index: 378

Text #11

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6562. Min Act: -0.1700

Data Index: 8686165 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6994. Min Act: -0.1700

Data Index: 4415495 (Open Web Text)

Max Activating Token Index: 512

Text #13

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6612. Min Act: -0.1700

Data Index: 2680921 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6558. Min Act: -0.1700

Data Index: 1998138 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6464. Min Act: -0.1700

Data Index: 6276226 (Open Web Text)

Max Activating Token Index: 892

Text #16

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6276. Min Act: -0.1700

Data Index: 2246026 (Open Web Text)

Max Activating Token Index: 572

Text #17

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6242. Min Act: -0.1700

Data Index: 4702740 (Open Web Text)

Max Activating Token Index: 307

Text #18

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6411. Min Act: -0.1700

Data Index: 3377958 (Open Web Text)

Max Activating Token Index: 264

Text #19

Max Range: 4.7736. Min Range: -4.7736

Max Act: 4.6210. Min Act: -0.1700

Data Index: 5326616 (Open Web Text)

Max Activating Token Index: 324