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

Dataset: Open Web Text

Neuron 1280 in Layer 4

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: 3.1637. Min Range: -3.1637

Max Act: 3.1637. Min Act: -0.1700

Data Index: 6722448 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.1637. Min Act: -0.1700

Data Index: 1678809 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.1637. Min Act: -0.1700

Data Index: 620538 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.1550. Min Act: -0.1700

Data Index: 1035785 (Open Web Text)

Max Activating Token Index: 391

Text #4

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0642. Min Act: -0.1700

Data Index: 7476032 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0436. Min Act: -0.1700

Data Index: 4177335 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 3.1637. Min Range: -3.1637

Max Act: 3.0212. Min Act: -0.1700

Data Index: 1708848 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9886. Min Act: -0.1700

Data Index: 5334484 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9729. Min Act: -0.1700

Data Index: 6480659 (Open Web Text)

Max Activating Token Index: 418

Text #9

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9831. Min Act: -0.1700

Data Index: 785691 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9587. Min Act: -0.1700

Data Index: 8628795 (Open Web Text)

Max Activating Token Index: 513

Text #11

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9554. Min Act: -0.1700

Data Index: 7814352 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9611. Min Act: -0.1700

Data Index: 4403003 (Open Web Text)

Max Activating Token Index: 554

Text #13

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9602. Min Act: -0.1700

Data Index: 113126 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9672. Min Act: -0.1700

Data Index: 889829 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9489. Min Act: -0.1700

Data Index: 373467 (Open Web Text)

Max Activating Token Index: 25

Text #16

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9683. Min Act: -0.1700

Data Index: 7087519 (Open Web Text)

Max Activating Token Index: 43

Text #17

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9451. Min Act: -0.1700

Data Index: 2746202 (Open Web Text)

Max Activating Token Index: 31

Text #18

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9417. Min Act: -0.1700

Data Index: 4702742 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 3.1637. Min Range: -3.1637

Max Act: 2.9434. Min Act: -0.1700

Data Index: 2296704 (Open Web Text)

Max Activating Token Index: 71