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

Dataset: Open Web Text

Neuron 1063 in Layer 6

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: 3.4421. Min Range: -3.4421

Max Act: 3.4421. Min Act: -0.1700

Data Index: 2999092 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.3310. Min Act: -0.1700

Data Index: 8267582 (Open Web Text)

Max Activating Token Index: 822

Text #2

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2582. Min Act: -0.1700

Data Index: 6055107 (Open Web Text)

Max Activating Token Index: 60

Text #3

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2434. Min Act: -0.1700

Data Index: 7092752 (Open Web Text)

Max Activating Token Index: 712

Text #4

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2318. Min Act: -0.1700

Data Index: 3010905 (Open Web Text)

Max Activating Token Index: 195

Text #5

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2210. Min Act: -0.1700

Data Index: 720650 (Open Web Text)

Max Activating Token Index: 42

Text #6

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2443. Min Act: -0.1700

Data Index: 4452334 (Open Web Text)

Max Activating Token Index: 134

Text #7

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2350. Min Act: -0.1700

Data Index: 7478199 (Open Web Text)

Max Activating Token Index: 508

Text #8

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.2087. Min Act: -0.1700

Data Index: 2038483 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1923. Min Act: -0.1700

Data Index: 2553771 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1834. Min Act: -0.1700

Data Index: 4379504 (Open Web Text)

Max Activating Token Index: 836

Text #11

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1751. Min Act: -0.1700

Data Index: 2048638 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1647. Min Act: -0.1700

Data Index: 1755297 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1773. Min Act: -0.1700

Data Index: 8528906 (Open Web Text)

Max Activating Token Index: 486

Text #14

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1673. Min Act: -0.1700

Data Index: 816916 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1646. Min Act: -0.1700

Data Index: 4411079 (Open Web Text)

Max Activating Token Index: 340

Text #16

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1649. Min Act: -0.1700

Data Index: 4886378 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1683. Min Act: -0.1700

Data Index: 6724559 (Open Web Text)

Max Activating Token Index: 41

Text #18

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1393. Min Act: -0.1700

Data Index: 5451500 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 3.4421. Min Range: -3.4421

Max Act: 3.1383. Min Act: -0.1700

Data Index: 2567605 (Open Web Text)

Max Activating Token Index: 81