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

Dataset: Open Web Text

Neuron 659 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: 6.8746. Min Range: -6.8746

Max Act: 6.8746. Min Act: -0.1700

Data Index: 5394520 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 6.8746. Min Range: -6.8746

Max Act: 6.8180. Min Act: -0.1700

Data Index: 6231824 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 6.8746. Min Range: -6.8746

Max Act: 6.7014. Min Act: -0.1700

Data Index: 3559697 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 6.8746. Min Range: -6.8746

Max Act: 6.4274. Min Act: -0.1700

Data Index: 921642 (Open Web Text)

Max Activating Token Index: 866

Text #4

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.7674. Min Act: -0.1700

Data Index: 4669144 (Open Web Text)

Max Activating Token Index: 143

Text #5

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.7513. Min Act: -0.1700

Data Index: 4701849 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.6128. Min Act: -0.1700

Data Index: 7039996 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.6573. Min Act: -0.1700

Data Index: 4187871 (Open Web Text)

Max Activating Token Index: 263

Text #8

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.5847. Min Act: -0.1700

Data Index: 2156890 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.5186. Min Act: -0.1700

Data Index: 3904176 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.5851. Min Act: -0.1700

Data Index: 7926685 (Open Web Text)

Max Activating Token Index: 671

Text #11

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.4859. Min Act: -0.1700

Data Index: 3559703 (Open Web Text)

Max Activating Token Index: 632

Text #12

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.5040. Min Act: -0.1700

Data Index: 4048543 (Open Web Text)

Max Activating Token Index: 315

Text #13

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.4543. Min Act: -0.1700

Data Index: 1673166 (Open Web Text)

Max Activating Token Index: 215

Text #14

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.4448. Min Act: -0.1700

Data Index: 7760142 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.4203. Min Act: -0.1700

Data Index: 3201864 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.3981. Min Act: -0.1700

Data Index: 5119111 (Open Web Text)

Max Activating Token Index: 355

Text #17

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.4304. Min Act: -0.1700

Data Index: 7569485 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.3269. Min Act: -0.1700

Data Index: 7867529 (Open Web Text)

Max Activating Token Index: 388

Text #19

Max Range: 6.8746. Min Range: -6.8746

Max Act: 5.3365. Min Act: -0.1700

Data Index: 6329999 (Open Web Text)

Max Activating Token Index: 322