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

Dataset: Open Web Text

Neuron 2609 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: 6.8596. Min Range: -6.8596

Max Act: 6.8596. Min Act: -0.1700

Data Index: 3690749 (Open Web Text)

Max Activating Token Index: 697

Text #1

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.8386. Min Act: -0.1700

Data Index: 7593535 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.7740. Min Act: -0.1700

Data Index: 1125554 (Open Web Text)

Max Activating Token Index: 154

Text #3

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.6819. Min Act: -0.1700

Data Index: 1399608 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.6121. Min Act: -0.1700

Data Index: 2715661 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.5855. Min Act: -0.1700

Data Index: 815334 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.5386. Min Act: -0.1700

Data Index: 2849549 (Open Web Text)

Max Activating Token Index: 104

Text #7

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4763. Min Act: -0.1700

Data Index: 3769697 (Open Web Text)

Max Activating Token Index: 837

Text #8

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4882. Min Act: -0.1700

Data Index: 3350631 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4959. Min Act: -0.1700

Data Index: 7036232 (Open Web Text)

Max Activating Token Index: 67

Text #10

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4881. Min Act: -0.1700

Data Index: 447333 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.5566. Min Act: -0.1700

Data Index: 516028 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4801. Min Act: -0.1700

Data Index: 5117100 (Open Web Text)

Max Activating Token Index: 483

Text #13

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4780. Min Act: -0.1700

Data Index: 1209899 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4524. Min Act: -0.1700

Data Index: 3832703 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.5142. Min Act: -0.1700

Data Index: 662100 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4368. Min Act: -0.1700

Data Index: 3487808 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4326. Min Act: -0.1700

Data Index: 1860455 (Open Web Text)

Max Activating Token Index: 250

Text #18

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4260. Min Act: -0.1700

Data Index: 180210 (Open Web Text)

Max Activating Token Index: 595

Text #19

Max Range: 6.8596. Min Range: -6.8596

Max Act: 6.4048. Min Act: -0.1700

Data Index: 5242168 (Open Web Text)

Max Activating Token Index: 828