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

Dataset: Open Web Text

Neuron 121 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: 4.2857. Min Range: -4.2857

Max Act: 4.2857. Min Act: -0.1700

Data Index: 1654884 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.2538. Min Act: -0.1700

Data Index: 2432430 (Open Web Text)

Max Activating Token Index: 781

Text #2

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.2042. Min Act: -0.1700

Data Index: 8113454 (Open Web Text)

Max Activating Token Index: 64

Text #3

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.1509. Min Act: -0.1700

Data Index: 5224510 (Open Web Text)

Max Activating Token Index: 414

Text #4

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0828. Min Act: -0.1700

Data Index: 2324099 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.1007. Min Act: -0.1700

Data Index: 5415370 (Open Web Text)

Max Activating Token Index: 963

Text #6

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0843. Min Act: -0.1700

Data Index: 750579 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0698. Min Act: -0.1700

Data Index: 8650413 (Open Web Text)

Max Activating Token Index: 489

Text #8

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0461. Min Act: -0.1700

Data Index: 954639 (Open Web Text)

Max Activating Token Index: 951

Text #9

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0416. Min Act: -0.1700

Data Index: 7992347 (Open Web Text)

Max Activating Token Index: 671

Text #10

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0311. Min Act: -0.1700

Data Index: 8733977 (Open Web Text)

Max Activating Token Index: 878

Text #11

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0095. Min Act: -0.1700

Data Index: 6274514 (Open Web Text)

Max Activating Token Index: 623

Text #12

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0306. Min Act: -0.1700

Data Index: 8173824 (Open Web Text)

Max Activating Token Index: 713

Text #13

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0071. Min Act: -0.1700

Data Index: 2474978 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0342. Min Act: -0.1700

Data Index: 8238872 (Open Web Text)

Max Activating Token Index: 540

Text #15

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0260. Min Act: -0.1700

Data Index: 5201868 (Open Web Text)

Max Activating Token Index: 509

Text #16

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0254. Min Act: -0.1700

Data Index: 6087274 (Open Web Text)

Max Activating Token Index: 675

Text #17

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0421. Min Act: -0.1700

Data Index: 1890355 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 4.2857. Min Range: -4.2857

Max Act: 4.0139. Min Act: -0.1700

Data Index: 4162522 (Open Web Text)

Max Activating Token Index: 350

Text #19

Max Range: 4.2857. Min Range: -4.2857

Max Act: 3.9977. Min Act: -0.1700

Data Index: 4544558 (Open Web Text)

Max Activating Token Index: 793