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

Dataset: Open Web Text

Neuron 96 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: 3.0056. Min Range: -3.0056

Max Act: 3.0056. Min Act: -0.1700

Data Index: 1168015 (Open Web Text)

Max Activating Token Index: 830

Text #1

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.9594. Min Act: -0.1700

Data Index: 2243656 (Open Web Text)

Max Activating Token Index: 357

Text #2

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.9440. Min Act: -0.1700

Data Index: 1853939 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8963. Min Act: -0.1700

Data Index: 8403172 (Open Web Text)

Max Activating Token Index: 872

Text #4

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.9003. Min Act: -0.1700

Data Index: 4817939 (Open Web Text)

Max Activating Token Index: 801

Text #5

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8886. Min Act: -0.1700

Data Index: 6214732 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8846. Min Act: -0.1700

Data Index: 5476734 (Open Web Text)

Max Activating Token Index: 713

Text #7

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8758. Min Act: -0.1700

Data Index: 1185558 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8845. Min Act: -0.1700

Data Index: 8056702 (Open Web Text)

Max Activating Token Index: 756

Text #9

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8654. Min Act: -0.1700

Data Index: 2581187 (Open Web Text)

Max Activating Token Index: 982

Text #10

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8631. Min Act: -0.1700

Data Index: 154234 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8753. Min Act: -0.1700

Data Index: 2852023 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8647. Min Act: -0.1700

Data Index: 5327165 (Open Web Text)

Max Activating Token Index: 710

Text #13

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8429. Min Act: -0.1700

Data Index: 6759315 (Open Web Text)

Max Activating Token Index: 393

Text #14

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8652. Min Act: -0.1700

Data Index: 7620956 (Open Web Text)

Max Activating Token Index: 908

Text #15

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8440. Min Act: -0.1700

Data Index: 5606655 (Open Web Text)

Max Activating Token Index: 922

Text #16

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8418. Min Act: -0.1700

Data Index: 3029531 (Open Web Text)

Max Activating Token Index: 978

Text #17

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8370. Min Act: -0.1700

Data Index: 6543798 (Open Web Text)

Max Activating Token Index: 791

Text #18

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8285. Min Act: -0.1700

Data Index: 402850 (Open Web Text)

Max Activating Token Index: 597

Text #19

Max Range: 3.0056. Min Range: -3.0056

Max Act: 2.8131. Min Act: -0.1700

Data Index: 943033 (Open Web Text)

Max Activating Token Index: 796