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

Dataset: Open Web Text

Neuron 965 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: 3.3015. Min Range: -3.3015

Max Act: 3.3015. Min Act: -0.1700

Data Index: 4564459 (Open Web Text)

Max Activating Token Index: 268

Text #1

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.2760. Min Act: -0.1700

Data Index: 6618032 (Open Web Text)

Max Activating Token Index: 619

Text #2

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.2589. Min Act: -0.1700

Data Index: 1182192 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.2671. Min Act: -0.1700

Data Index: 4208724 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.2319. Min Act: -0.1700

Data Index: 934130 (Open Web Text)

Max Activating Token Index: 734

Text #5

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.2162. Min Act: -0.1700

Data Index: 5592751 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1716. Min Act: -0.1700

Data Index: 2722727 (Open Web Text)

Max Activating Token Index: 689

Text #7

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1834. Min Act: -0.1700

Data Index: 7222483 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1720. Min Act: -0.1700

Data Index: 7846950 (Open Web Text)

Max Activating Token Index: 412

Text #9

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1765. Min Act: -0.1700

Data Index: 2406083 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1607. Min Act: -0.1700

Data Index: 5355747 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1524. Min Act: -0.1700

Data Index: 3766086 (Open Web Text)

Max Activating Token Index: 312

Text #12

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1375. Min Act: -0.1700

Data Index: 1836544 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1292. Min Act: -0.1700

Data Index: 8593547 (Open Web Text)

Max Activating Token Index: 339

Text #14

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1308. Min Act: -0.1700

Data Index: 3448138 (Open Web Text)

Max Activating Token Index: 404

Text #15

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1383. Min Act: -0.1700

Data Index: 1250270 (Open Web Text)

Max Activating Token Index: 779

Text #16

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1153. Min Act: -0.1700

Data Index: 7747917 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1177. Min Act: -0.1700

Data Index: 5682208 (Open Web Text)

Max Activating Token Index: 782

Text #18

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1393. Min Act: -0.1700

Data Index: 7096266 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 3.3015. Min Range: -3.3015

Max Act: 3.1350. Min Act: -0.1700

Data Index: 3700624 (Open Web Text)

Max Activating Token Index: 174